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
     Hey
    -0.07
    ，可
    -0.07
    ±ظ
    -0.06
    ，无
    -0.06
    ，说
    -0.06
     лишь
    -0.06
    _cmp
    -0.06
     bottled
    -0.06
     mulher
    -0.06
     mücadele
    -0.06
    POSITIVE LOGITS
     série
    0.07
    _areas
    0.06
    nestjs
    0.06
    별
    0.06
    	method
    0.06
    umat
    0.06
    -small
    0.06
     imdb
    0.06
     #__
    0.06
    功
    0.06
    Act Density 0.000%

    No Known Activations