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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and their components

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

    mathematical relations over symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OCCURRED
    -0.39
     betweenstory
    -0.37
     découver
    -0.37
    SequentialGroup
    -0.36
     commerciales
    -0.36
     internationaux
    -0.36
    arrête
    -0.36
    cargador
    -0.35
     fédé
    -0.35
     prêts
    -0.35
    POSITIVE LOGITS
     AssemblyCulture
    0.71
    queryInterface
    0.52
     transfieras
    0.52
    $_['
    0.51
    WriteAttribute
    0.50
    LEncoder
    0.49
     Vikipedi
    0.48
     Dry
    0.46
    хьтан
    0.46
     inge
    0.45
    Act Density 0.219%

    No Known Activations