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

    Neuronpedia

    INDEX
    Explanations

    code execution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    我没
    -0.08
    _PRIORITY
    -0.07
     GetById
    -0.07
     GIVEN
    -0.07
     كب
    -0.07
    _MISS
    -0.07
    みたいです
    -0.07
     zelf
    -0.07
    Ĭ
    -0.07
     itch
    -0.06
    POSITIVE LOGITS
    .B
    0.07
     debates
    0.07
     experiments
    0.07
     cozy
    0.07
    道德
    0.07
     étaient
    0.07
    皂
    0.06
    ﯠ
    0.06
    ᠪ
    0.06
    น
    0.06
    Act Density 0.094%

    No Known Activations