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

    Neuronpedia

    INDEX
    Explanations

    site

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    反
    -0.07
    ﰀ
    -0.07
    ŏ
    -0.07
     adverse
    -0.07
    atform
    -0.06
    ࡒ
    -0.06
    _combined
    -0.06
     promoted
    -0.06
    UILabel
    -0.06
    פר
    -0.06
    POSITIVE LOGITS
     Steam
    0.07
     cinemat
    0.07
     الحي
    0.06
     Cylinder
    0.06
    生产车间
    0.06
    .syntax
    0.06
    舍得
    0.06
    .YEAR
    0.06
    remium
    0.06
    ⏩
    0.06
    Act Density 0.000%

    No Known Activations