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
     sample
    -0.07
     it
    -0.07
    рещ
    -0.07
     lest
    -0.07
     auss
    -0.06
    再
    -0.06
     Fine
    -0.06
     TEM
    -0.06
    (N
    -0.06
    .dispatch
    -0.06
    POSITIVE LOGITS
     harming
    0.08
    Parameters
    0.06
    _places
    0.06
    .CheckedChanged
    0.06
    xBB
    0.06
    .Matcher
    0.06
    _WINDOWS
    0.06
    .Boolean
    0.06
    탕
    0.06
    .filtered
    0.06
    Act Density 1.157%

    No Known Activations