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

    Neuronpedia

    INDEX
    Explanations

    math/code/symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不锈钢
    -0.07
    	Data
    -0.07
     kişinin
    -0.07
     vener
    -0.06
    执业
    -0.06
    降幅
    -0.06
    生长
    -0.06
    %"><
    -0.06
    民用
    -0.06
    _deposit
    -0.06
    POSITIVE LOGITS
    (↵↵
    0.07
     그리스
    0.07
    indice
    0.06
    afd
    0.06
    לחץ
    0.06
    おすす
    0.06
    ucci
    0.06
    시
    0.06
    atti
    0.06
    цу
    0.06
    Act Density 0.232%

    No Known Activations