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

    Neuronpedia

    INDEX
    Explanations

    Web content snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mac
    -0.07
     egregious
    -0.07
    ﰀ
    -0.07
    뛴
    -0.07
    觉悟
    -0.06
     flash
    -0.06
    cod
    -0.06
     amateur
    -0.06
    Patterns
    -0.06
     Ston
    -0.06
    POSITIVE LOGITS
     Dinner
    0.08
    SZ
    0.07
    ດ
    0.07
    WindowState
    0.07
     internals
    0.07
     אליה
    0.07
    -dependent
    0.07
    omba
    0.07
    щение
    0.07
     Deliver
    0.07
    Act Density 0.034%

    No Known Activations