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

    Neuronpedia

    INDEX
    Explanations

    en

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Real
    -0.07
     ''),
    -0.06
     hor
    -0.06
     tale
    -0.06
     соль
    -0.06
     raced
    -0.06
    わず
    -0.06
    ických
    -0.06
    _Sub
    -0.06
     spanking
    -0.06
    POSITIVE LOGITS
    _backend
    0.06
     xứ
    0.06
    醒
    0.06
     budding
    0.06
    mit
    0.06
    lobals
    0.06
    fal
    0.06
    ycle
    0.06
    /QĐ
    0.06
    NSUInteger
    0.06
    Act Density 0.001%

    No Known Activations