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

    Neuronpedia

    INDEX
    Explanations

    nouns and adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    withErrors
    -0.08
     coerc
    -0.07
    開放
    -0.07
    _padding
    -0.07
    RenderWindow
    -0.07
    лага
    -0.07
    below
    -0.07
    组织领导
    -0.07
     Constitutional
    -0.07
    ATEST
    -0.07
    POSITIVE LOGITS
    货物
    0.07
    大腿
    0.07
    รวจ
    0.06
    (↵↵
    0.06
    (character
    0.06
    コー
    0.06
    🅽
    0.06
     thị
    0.06
    خدام
    0.06
    物品
    0.06
    Act Density 0.015%

    No Known Activations