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

    Neuronpedia

    INDEX
    Explanations

    numeric variables and function calls in programming code

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

    Appears before short, seemingly random strings

    np_acts-logits-general · gemini-2.0-flash

    Award in, give a, group of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.72
    GraphicsUnit
    -0.68
    TypedDataSet
    -0.63
    DebuggerNonUser
    -0.57
    Geplaatst
    -0.56
    ContentAlignment
    -0.56
    kloped
    -0.56
    CodeAttribute
    -0.51
    localctx
    -0.51
    XMLSchema
    -0.51
    POSITIVE LOGITS
    الحياه
    0.61
    kmale
    0.61
    НИК
    0.59
     antem
    0.59
    '):
    0.58
    '])->
    0.55
    $$
    0.55
    $_,
    0.54
    ftagPool
    0.54
    }.
    0.53
    Act Density 0.042%

    No Known Activations