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

    Neuronpedia

    INDEX
    Explanations

    injection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    であ
    -0.07
    .Speed
    -0.07
    _relu
    -0.07
     see
    -0.06
    Merge
    -0.06
     Philosophy
    -0.06
     quant
    -0.06
     ['
    -0.06
     toàn
    -0.06
    高等
    -0.06
    POSITIVE LOGITS
    gb
    0.07
     Cent
    0.06
    ney
    0.06
    NEY
    0.06
    供应
    0.06
    喊
    0.06
    icture
    0.06
    failure
    0.06
     земель
    0.06
     vale
    0.06
    Act Density 0.002%

    No Known Activations