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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical expressions

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

    numbers and decimals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.60
    writeFieldEnd
    -0.54
     considérons
    -0.53
    -0.52
    期刊论文
    -0.52
    rrggbb
    -0.50
    cookieParser
    -0.50
    complexContent
    -0.50
    Hochspringen
    -0.48
     Irán
    -0.48
    POSITIVE LOGITS
    GTCX
    0.46
     decimals
    0.38
    IsMutable
    0.37
     оча
    0.36
    arf
    0.35
    DOCTYPE
    0.35
     ontvangen
    0.35
    strptime
    0.35
    __*/
    0.35
     voorzien
    0.34
    Act Density 0.536%

    No Known Activations