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

    Neuronpedia

    INDEX
    Explanations

    punctuation or period separations in text

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

    names and places after St

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.66
    uxxxx
    -0.62
    -0.61
     typelib
    -0.58
    GOTREF
    -0.57
    FunctionFlags
    -0.57
    FromNib
    -0.57
    ágenes
    -0.57
    libatkan
    -0.57
    randomUUID
    -0.56
    POSITIVE LOGITS
     Saint
    0.77
     St
    0.70
    Saint
    0.67
    St
    0.59
     SAINT
    0.56
     saint
    0.52
     Sankt
    0.48
     State
    0.45
     Saints
    0.44
     San
    0.44
    Act Density 0.004%

    No Known Activations