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

    Neuronpedia

    INDEX
    Explanations

    g

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (menu
    -0.08
    rejected
    -0.06
    Segoe
    -0.06
     judged
    -0.06
    ‌ی
    -0.06
     gå
    -0.06
    Tokens
    -0.06
    !(↵
    -0.06
    yg
    -0.06
     мають
    -0.06
    POSITIVE LOGITS
     Пра
    0.07
    _DEFINED
    0.07
     جستارهای
    0.06
     ngOn
    0.06
    _Map
    0.06
    ,nil
    0.06
     glyph
    0.06
     HK
    0.06
    _paper
    0.06
     hã
    0.06
    Act Density 0.174%

    No Known Activations