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

    Neuronpedia

    INDEX
    Explanations

    references to internal and external factors or processes

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

    internal properties and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     müſſen
    -0.71
    rophoresis
    -0.69
     laſſen
    -0.69
     étoient
    -0.68
     getRule
    -0.66
     queſta
    -0.65
     Majefty
    -0.65
    ckså
    -0.65
    SEGUIR
    -0.65
     gages
    -0.64
    POSITIVE LOGITS
     internal
    2.13
     Internal
    1.91
    internal
    1.91
    Internal
    1.87
     INTERNAL
    1.72
    INTERNAL
    1.63
     internally
    1.43
     wewnętr
    1.23
     interno
    1.23
     internos
    1.19
    Act Density 0.016%

    No Known Activations