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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication and social interactions

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

    discussing family matters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.68
     preventative
    -0.68
     interpretive
    -0.61
    agerie
    -0.60
     gleaned
    -0.59
    spanning
    -0.58
     leapt
    -0.57
    checkFor
    -0.57
    issipp
    -0.56
     egregious
    -0.56
    POSITIVE LOGITS
    ChildScrollView
    0.81
     Nowadays
    0.65
    Nowadays
    0.60
    Moreover
    0.58
     nowadays
    0.58
     shrimps
    0.55
     Moreover
    0.54
     equipments
    0.54
     freezed
    0.52
     respectivas
    0.47
    Act Density 11.630%

    No Known Activations