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

    Neuronpedia

    INDEX
    Explanations

    impacted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _M
    -0.06
    secondary
    -0.06
    ávě
    -0.06
    Filed
    -0.05
    	DEBUG
    -0.05
    icense
    -0.05
     _
    -0.05
    .Common
    -0.05
    .look
    -0.05
     opi
    -0.05
    POSITIVE LOGITS
    (cos
    0.07
    ğını
    0.07
    .setFont
    0.07
     mož
    0.07
     الرح
    0.07
    xt
    0.07
    [J
    0.06
     القرآن
    0.06
     看
    0.06
     montage
    0.06
    Act Density 0.000%

    No Known Activations