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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     tents
    -0.07
    _slots
    -0.06
    gypt
    -0.06
    ouples
    -0.06
    atal
    -0.06
    istingu
    -0.06
    atu
    -0.06
    usive
    -0.06
     Returns
    -0.06
    POSITIVE LOGITS
     بت
    0.07
     rather
    0.06
    矢
    0.06
    /assert
    0.06
     य
    0.06
    尼亚
    0.06
     解
    0.06
     hton
    0.06
    .Align
    0.06
     fairly
    0.06
    Act Density 0.014%

    No Known Activations