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

    Neuronpedia

    INDEX
    Explanations

    sequences of whitespace characters

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

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.59
    ReusableCell
    -0.57
    QMetaType
    -0.47
     HasFactory
    -0.45
    AddTagHelper
    -0.43
     Forderung
    -0.40
    浓郁
    -0.37
     ***!
    -0.37
     Forderungen
    -0.36
     diejenigen
    -0.36
    POSITIVE LOGITS
    extAlignment
    0.59
    Derbyniad
    0.56
    Jeografia
    0.48
     '\\;'
    0.47
    └──
    0.47
    &
    0.45
    ntax
    0.45
     Perceived
    0.44
     опо
    0.44
     hoarse
    0.44
    Act Density 0.121%

    No Known Activations