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

    Neuronpedia

    INDEX
    Explanations

    negations and conditions related to actions and events

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

    actual or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Parcelize
    -0.72
    ="@+
    -0.67
    parsedMessage
    -0.66
    BufferException
    -0.65
    AndEndTag
    -0.65
    Personensuche
    -0.64
    IntoConstraints
    -0.62
     wireType
    -0.62
    SharedCtor
    -0.62
     Numerade
    -0.61
    POSITIVE LOGITS
     actual
    1.20
     actually
    1.19
    実際に
    1.05
    actual
    1.04
    actually
    0.94
     Actually
    0.85
    Actual
    0.85
     tatsächlich
    0.84
     Actual
    0.84
    実際
    0.83
    Act Density 0.149%

    No Known Activations