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

    Neuronpedia

    INDEX
    Explanations

    online warnings/problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    卡
    -0.07
    ्यप
    -0.07
    Psy
    -0.07
    -Jun
    -0.07
    -spot
    -0.07
     примі
    -0.06
    -hand
    -0.06
    ера
    -0.06
     CSRF
    -0.06
    lich
    -0.06
    POSITIVE LOGITS
     Mosul
    0.06
     tirelessly
    0.06
     colorWithRed
    0.06
    زد
    0.06
    (directory
    0.06
     darken
    0.06
    _xlabel
    0.06
     نبود
    0.06
    (completion
    0.06
    ापक
    0.06
    Act Density 0.029%

    No Known Activations