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

    Neuronpedia

    INDEX
    Explanations

    code-related functions and methods in programming contexts

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

    code snippets computing indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.74
    DIPSETTING
    -0.63
    EDEFAULT
    -0.61
    AddTagHelper
    -0.60
    Personendaten
    -0.59
     للاسماء
    -0.59
    يميديا
    -0.59
     виправивши
    -0.57
     CallOverrides
    -0.56
    SourceChecksum
    -0.56
    POSITIVE LOGITS
    bolista
    0.44
    schirm
    0.32
     skew
    0.31
     physique
    0.31
     Anspruch
    0.31
    prüfung
    0.30
    hoeddwyd
    0.29
     differentiation
    0.28
     prompt
    0.28
     estekak
    0.28
    Act Density 0.178%

    No Known Activations