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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical or statistical terms related to regression and regularization

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

    small values and limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.45
    méno
    -0.40
     voorzien
    -0.34
     zufolge
    -0.33
     disambiguazione
    -0.33
     daarvan
    -0.33
    icode
    -0.32
     Träger
    -0.32
     Traducción
    -0.32
    parsedMessage
    -0.31
    POSITIVE LOGITS
     extre
    0.51
    TypedDataSet
    0.51
    /**
    0.49
     extrema
    0.48
     extrême
    0.47
     extremes
    0.47
     extreme
    0.46
    AccessFile
    0.46
    kháu
    0.46
    posedge
    0.43
    Act Density 0.113%

    No Known Activations