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

    Neuronpedia

    INDEX
    Explanations

    complex sentence structures and their components

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

    excess or overload

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rawDesc
    -0.43
    parsedMessage
    -0.43
    msgTypes
    -0.42
    xase
    -0.38
     *>(
    -0.36
    Geplaatst
    -0.36
     utafiti
    -0.35
    }(),
    -0.34
    fellow
    -0.34
     Dä
    -0.32
    POSITIVE LOGITS
     exceso
    0.91
     excesso
    0.91
     excess
    0.90
     Excess
    0.84
     overloaded
    0.84
    Excess
    0.84
    excess
    0.82
     overload
    0.82
     excesses
    0.81
     excès
    0.79
    Act Density 0.126%

    No Known Activations