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

    Neuronpedia

    INDEX
    Explanations

    citation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unk
    -0.07
    醬
    -0.07
    (itr
    -0.06
    _dropdown
    -0.06
    ＿
    -0.06
     denominator
    -0.06
     terra
    -0.06
    dq
    -0.06
    ся
    -0.06
    黨
    -0.06
    POSITIVE LOGITS
     المباشر
    0.07
    stinence
    0.07
    -expression
    0.07
    手游
    0.07
    穿搭
    0.06
    无意
    0.06
    retrieve
    0.06
    教程
    0.06
     opposes
    0.06
     fallout
    0.06
    Act Density 0.002%

    No Known Activations