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

    Neuronpedia

    INDEX
    Explanations

    What

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _rule
    -0.07
    黑恶势力
    -0.07
    一生
    -0.07
     리스트
    -0.07
    (ins
    -0.06
     نيوز
    -0.06
     Advice
    -0.06
    考试
    -0.06
    _degree
    -0.06
     enlist
    -0.06
    POSITIVE LOGITS
    łam
    0.07
    /portfolio
    0.07
    ipi
    0.07
     ske
    0.07
    ﾖ
    0.07
    ǃ
    0.06
    _SC
    0.06
     poco
    0.06
     asks
    0.06
    głos
    0.06
    Act Density 0.002%

    No Known Activations