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

    Neuronpedia

    INDEX
    Explanations

    os

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Snake
    -0.07
    Snake
    -0.07
     vene
    -0.06
    _suite
    -0.06
    APA
    -0.06
     stra
    -0.06
     برخورد
    -0.06
    owing
    -0.06
     Contrast
    -0.06
    普
    -0.06
    POSITIVE LOGITS
     ')
↵
    0.08
    os
    0.08
     ان
    0.08
    ♪↵↵
    0.07
    OS
    0.07
    台
    0.07
                ↵
    0.07
     دانش
    0.06
     OS
    0.06
    biz
    0.06
    Act Density 0.006%

    No Known Activations