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

    Neuronpedia

    INDEX
    Explanations

    cooking-related actions and instructions

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

    `<start_of_turn> user`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الحياه
    -0.47
     ainfi
    -0.47
    cesis
    -0.46
    erschutz
    -0.43
     opérés
    -0.43
     vald
    -0.42
     noires
    -0.42
     rhestr
    -0.42
    RTGC
    -0.42
    endpush
    -0.41
    POSITIVE LOGITS
    parsedMessage
    0.47
    Kent
    0.41
    IsContent
    0.41
    Hochspringen
    0.40
    تفصیلات
    0.40
     ujednoznacz
    0.39
     &___
    0.38
    MLLoader
    0.38
    TypedDataSet
    0.36
    中には
    0.36
    Act Density 0.010%

    No Known Activations