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

    Neuronpedia

    INDEX
    Explanations

    post

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bew
    -0.07
    ቱ
    -0.07
     anxious
    -0.07
    沚
    -0.07
    $str
    -0.07
    receipt
    -0.07
    主播
    -0.07
    CLUDING
    -0.06
    Interested
    -0.06
    (visitor
    -0.06
    POSITIVE LOGITS
    立即
    0.08
    ).[
    0.07
    车辆
    0.07
    _FUNC
    0.07
    íc
    0.07
    酷
    0.07
    مبادئ
    0.07
    économie
    0.07
    abras
    0.07
    ::~
    0.07
    Act Density 0.001%

    No Known Activations