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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    损伤
    -0.07
    ذهب
    -0.06
    ira
    -0.06
    sharp
    -0.06
    ZIP
    -0.06
     Iv
    -0.06
    fun
    -0.06
     compile
    -0.06
    alım
    -0.06
    Fade
    -0.06
    POSITIVE LOGITS
    liable
    0.07
    ർ
    0.07
    ころ
    0.07
    凡是
    0.07
     Detect
    0.07
    工期
    0.06
    -stage
    0.06
    ಟ
    0.06
    _centers
    0.06
    (ss
    0.06
    Act Density 0.000%

    No Known Activations