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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     karde
    -0.08
    稚
    -0.07
    startsWith
    -0.07
    virt
    -0.07
    視
    -0.07
    跆
    -0.07
    كسر
    -0.07
     внешне
    -0.07
    خطأ
    -0.06
    	RuntimeObject
    -0.06
    POSITIVE LOGITS
    *A
    0.07
     detect
    0.07
     sometimes
    0.07
     Tome
    0.07
    にも
    0.07
    푱
    0.07
     perform
    0.07
    上海
    0.06
    [](
    0.06
    iform
    0.06
    Act Density 0.001%

    No Known Activations