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

    Neuronpedia

    INDEX
    Explanations

    occurrences of accidental actions and the consequences of those actions

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

    accidental falls or drops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ration
    -0.30
     Ration
    -0.30
    welle
    -0.30
    ęt
    -0.30
     ration
    -0.29
    anoma
    -0.29
     tiks
    -0.29
     nä
    -0.28
     avail
    -0.28
     morgen
    -0.28
    POSITIVE LOGITS
    RegressionTest
    0.82
    parsedMessage
    0.60
     InputDecoration
    0.60
     resourceCulture
    0.59
    encodeWith
    0.59
    stateProvider
    0.58
     betweenstory
    0.58
     ModelExpression
    0.56
     Biôgrafia
    0.56
    Rptr
    0.56
    Act Density 0.058%

    No Known Activations