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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Discount
    -0.06
    rin
    -0.06
    人类
    -0.06
     nir
    -0.06
    -factor
    -0.06
    (factor
    -0.06
     drowning
    -0.06
    ras
    -0.06
    Ich
    -0.06
    /hr
    -0.06
    POSITIVE LOGITS
     Listed
    0.08
    .Raw
    0.07
     изображ
    0.07
    _season
    0.06
     diseñador
    0.06
    (mt
    0.06
    _unsigned
    0.06
    _UNSIGNED
    0.06
    removeClass
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    Act Density 0.004%

    No Known Activations