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

    Neuronpedia

    INDEX
    Explanations

    uter

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     online
    -0.07
    _cor
    -0.07
    沾
    -0.07
    astr
    -0.07
    오
    -0.07
    online
    -0.07
    wr
    -0.07
    或者其他
    -0.07
    ا
    -0.07
    罢
    -0.07
    POSITIVE LOGITS
     Chill
    0.08
    될
    0.07
    Fixed
    0.07
     Amph
    0.07
    FontOfSize
    0.07
    حجم
    0.07
    égor
    0.07
    -category
    0.06
     cruiser
    0.06
     DISPLAY
    0.06
    Act Density 0.002%

    No Known Activations