Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    arithmetic operations and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    strings that contain identifiers or variables in code-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical equations or programming contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     généraux
    -0.53
     bassa
    -0.49
     diamants
    -0.47
     debout
    -0.46
     civiles
    -0.46
     internationaux
    -0.46
     tidligere
    -0.45
    AnimationsModule
    -0.45
     semplici
    -0.45
     différences
    -0.44
    POSITIVE LOGITS
     мәкал
    1.06
    rungsseite
    0.86
    цездатний
    0.78
     betweenstory
    0.77
     propOrder
    0.76
    MarshalTo
    0.74
    queryInterface
    0.73
     oprot
    0.73
    SharedDtor
    0.73
    Personendaten
    0.71
    Act Density 0.065%

    No Known Activations