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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fd
    -0.07
    致力于
    -0.07
    فشل
    -0.07
    管理部门
    -0.07
     frowned
    -0.06
     Pulitzer
    -0.06
    맏
    -0.06
     spirited
    -0.06
    enuine
    -0.06
    identify
    -0.06
    POSITIVE LOGITS
    /global
    0.08
    ⽬
    0.07
    保险
    0.07
     SQ
    0.07
    _RGBA
    0.07
    标
    0.07
    Ｋ
    0.06
     cran
    0.06
    _income
    0.06
     ARM
    0.06
    Act Density 0.006%

    No Known Activations