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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries related to technical topics or problem-solving

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

    Q: followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BorderSide
    -0.49
    itespace
    -0.49
     يتيمه
    -0.48
     Immer
    -0.45
    nicamente
    -0.44
     CONTIN
    -0.43
    enumii
    -0.43
     continues
    -0.43
    basicConfig
    -0.43
     permitir
    -0.42
    POSITIVE LOGITS
    Q
    2.11
     Q
    1.20
    q
    1.14
    Ｑ
    1.09
    QW
    0.93
    Qs
    0.93
    Qq
    0.79
    QJ
    0.78
    Qn
    0.77
    <bos>
    0.77
    Act Density 0.050%

    No Known Activations