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

    Neuronpedia

    INDEX
    Explanations

    General English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kendine
    -0.08
     gauss
    -0.07
    еров
    -0.06
    eah
    -0.06
    >X
    -0.06
    outh
    -0.06
    са
    -0.06
    _STA
    -0.06
    йте
    -0.06
    nas
    -0.06
    POSITIVE LOGITS
     Registr
    0.07
    										↵
    0.07
    删除
    0.07
     Krish
    0.06
    rollable
    0.06
     평균
    0.06
     chiropr
    0.06
    الة
    0.06
     처리
    0.06
     количе
    0.06
    Act Density 0.000%

    No Known Activations