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

    Neuronpedia

    INDEX
    Explanations

    quotation punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     onload
    -0.07
     ویکی
    -0.07
    _medium
    -0.07
    _disp
    -0.06
    MatrixMode
    -0.06
     Fourier
    -0.06
    िद
    -0.06
     observing
    -0.06
    	std
    -0.06
    endars
    -0.06
    POSITIVE LOGITS
    论坛
    0.06
    une
    0.06
     Unused
    0.06
    ifact
    0.06
    /frontend
    0.06
     họ
    0.06
     чином
    0.06
    worm
    0.06
     інститут
    0.06
     zen
    0.06
    Act Density 0.028%

    No Known Activations