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

    Neuronpedia

    INDEX
    Explanations

    Mixed content snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hated
    -0.06
    (Field
    -0.06
     Tara
    -0.06
    Barrier
    -0.06
    bagai
    -0.06
    pol
    -0.06
     wall
    -0.06
    (fname
    -0.06
    .Stretch
    -0.06
     Indicator
    -0.06
    POSITIVE LOGITS
     Flint
    0.07
     رئ
    0.07
     전에
    0.07
    elite
    0.07
    民族
    0.06
    xmlns
    0.06
     секрет
    0.06
    生物
    0.06
     deceive
    0.06
     baseman
    0.06
    Act Density 0.000%

    No Known Activations