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

    Neuronpedia

    INDEX
    Explanations

    terms related to input processing and predictions within machine learning models

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

    prediction on new data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.56
     BorderSide
    -0.52
    featureID
    -0.52
    jMenuItem
    -0.51
    typeorm
    -0.51
    енча
    -0.48
    {}",
    -0.48
    stateProvider
    -0.48
    MigrationBuilder
    -0.48
    Попис
    -0.48
    POSITIVE LOGITS
    Geplaatst
    0.38
     Росси
    0.32
    meldungen
    0.31
     bilo
    0.31
     pétrole
    0.30
    жнему
    0.30
     peito
    0.30
     bajos
    0.30
    /**
    0.30
    ynku
    0.29
    Act Density 0.127%

    No Known Activations