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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +f
    -0.06
    +C
    -0.06
     representa
    -0.06
     cov
    -0.06
     مدير
    -0.06
     Comput
    -0.06
    _subnet
    -0.06
    .fill
    -0.06
     καλύ
    -0.06
    Password
    -0.06
    POSITIVE LOGITS
    !↵↵
    0.07
    imum
    0.06
    !)↵
    0.06
    osc
    0.06
    ieu
    0.06
    (Array
    0.06
    .Photo
    0.06
    asticsearch
    0.06
    خانه
    0.06
    _cb
    0.06
    Act Density 0.004%

    No Known Activations