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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    忍受
    -0.08
     Ren
    -0.08
    一看
    -0.07
    影视
    -0.07
     "",
    -0.07
    哪裡
    -0.07
     mush
    -0.07
    	bs
    -0.07
     expensive
    -0.07
    .SH
    -0.07
    POSITIVE LOGITS
     medios
    0.07
    createQuery
    0.06
     submissions
    0.06
    Sorting
    0.06
    ॠ
    0.06
    悬念
    0.06
    评议
    0.06
    ととも
    0.06
     katılım
    0.06
     �
    0.06
    Act Density 0.096%

    No Known Activations