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

    Neuronpedia

    INDEX
    Explanations

    predictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sham
    -0.06
    give
    -0.06
    ZIP
    -0.06
     vivo
    -0.06
    둘
    -0.06
    Absolute
    -0.06
     worn
    -0.06
    	str
    -0.06
     있었다
    -0.06
     Blood
    -0.06
    POSITIVE LOGITS
    255
    0.08
    =".$
    0.07
    bral
    0.06
    /".$
    0.06
     rozsah
    0.06
    染
    0.06
    _DIFF
    0.06
     بالأ
    0.06
     requestCode
    0.06
    ラス
    0.06
    Act Density 0.071%

    No Known Activations