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

    Neuronpedia

    INDEX
    Explanations

    adaptation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wlan
    -0.08
    apes
    -0.08
     تجاه
    -0.08
    apache
    -0.08
    mega
    -0.07
     gcd
    -0.07
    ในการ
    -0.07
    Glass
    -0.07
    -gl
    -0.07
     throughout
    -0.07
    POSITIVE LOGITS
     conversion
    0.11
     Conversion
    0.10
     conversions
    0.10
    _conversion
    0.09
    转换
    0.09
    Conversion
    0.09
    .convert
    0.09
     रुप
    0.09
    小說
    0.08
     ناج
    0.08
    Act Density 0.020%

    No Known Activations