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

    Neuronpedia

    INDEX
    Explanations

    non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    색
    -0.08
     Load
    -0.07
    _PI
    -0.07
    iriş
    -0.07
    .Back
    -0.07
     הי
    -0.07
     Ud
    -0.06
    />.↵
    -0.06
    潦
    -0.06
     stall
    -0.06
    POSITIVE LOGITS
     comparatively
    0.08
     комфорт
    0.07
    俩
    0.07
    们
    0.07
    .lr
    0.07
    使劲
    0.06
    𝙯
    0.06
    又
    0.06
    筹建
    0.06
    给大家
    0.06
    Act Density 0.120%

    No Known Activations