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

    Neuronpedia

    INDEX
    Explanations

    elements related to context and usability

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

    used to be followed by position/state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     peuple
    -0.31
    paravant
    -0.29
    CGPoint
    -0.29
    Chất
    -0.28
     Censo
    -0.28
     procès
    -0.28
     royaume
    -0.28
    d
    -0.27
    some
    -0.27
    IDS
    -0.27
    POSITIVE LOGITS
    SharedDtor
    0.77
     uſed
    0.73
     myſelf
    0.66
     houſe
    0.64
    нгред
    0.62
     Houſe
    0.60
    enablog
    0.59
     itſelf
    0.59
    ロウィン
    0.57
     ſche
    0.57
    Act Density 0.044%

    No Known Activations