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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    创新驱动
    -0.07
     hide
    -0.07
    ourn
    -0.07
    ">
↵
↵
    -0.07
    notification
    -0.07
     vt
    -0.06
    车内
    -0.06
    Tony
    -0.06
    浓浓的
    -0.06
    的高度
    -0.06
    POSITIVE LOGITS
    zx
    0.07
    ul
    0.07
    шек
    0.07
     OS
    0.06
     Hyp
    0.06
    %E
    0.06
    TH
    0.06
     المشروع
    0.06
     METHODS
    0.06
    em
    0.06
    Act Density 0.006%

    No Known Activations