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

    Neuronpedia

    INDEX
    Explanations

    programming language constructs associated with traits and derivation

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

    equivalently, linear map

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.69
    LookAnd
    -0.66
    writeFieldEnd
    -0.66
     surla
    -0.66
    transQ
    -0.65
    uxxxx
    -0.62
     betweenstory
    -0.59
    stylers
    -0.59
    TypedDataSet
    -0.59
     esternos
    -0.59
    POSITIVE LOGITS
     PartialEq
    0.66
     differences
    0.35
     occasion
    0.35
     spørsmål
    0.35
    paravant
    0.35
    を取る
    0.33
    Ventajas
    0.32
     purpose
    0.32
     App
    0.32
     terms
    0.32
    Act Density 0.001%

    No Known Activations