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

    Neuronpedia

    INDEX
    Explanations

    Programming/Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     era
    -0.07
     بالرياض
    -0.06
    ropped
    -0.06
     eldre
    -0.06
    bottom
    -0.06
     Bergen
    -0.06
    登場
    -0.06
    桐
    -0.06
    [frame
    -0.06
    aji
    -0.06
    POSITIVE LOGITS
    split
    0.06
     Pol
    0.06
     suggest
    0.06
    برای
    0.06
    odeled
    0.06
    (sql
    0.06
    (lr
    0.06
    _internal
    0.06
    یشه
    0.06
     compressor
    0.06
    Act Density 0.033%

    No Known Activations