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

    Neuronpedia

    INDEX
    Explanations

    spoken dialogue or expressions of characters' emotional states

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

    soft-spoken people and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.69
    SourceChecksum
    -0.61
    évaluateur
    -0.58
    PostInfinity
    -0.58
     loud
    -0.57
    InjectAttribute
    -0.55
     CreateTagHelper
    -0.55
     QtWidgets
    -0.54
    AddTagHelper
    -0.54
    BeginContext
    -0.52
    POSITIVE LOGITS
     quietly
    0.46
    phosa
    0.44
    참고
    0.43
     understated
    0.42
    quiet
    0.38
    Quiet
    0.37
     calme
    0.34
     calmly
    0.34
    pecabezas
    0.34
     quiet
    0.33
    Act Density 0.030%

    No Known Activations