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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hq
    -0.08
     eu
    -0.07
     swallow
    -0.07
    steller
    -0.07
    眼镜
    -0.07
    ömür
    -0.07
     swipe
    -0.07
    ﾟ
    -0.07
    ﯨ
    -0.06
     pale
    -0.06
    POSITIVE LOGITS
     offences
    0.07
     misconduct
    0.07
    (fetch
    0.07
    刈
    0.07
    .parameters
    0.07
    גת
    0.07
     _)
    0.07
    тки
    0.07
    .getTotal
    0.07
    FDA
    0.07
    Act Density 0.098%

    No Known Activations