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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    趁
    -0.07
    emption
    -0.06
    反腐
    -0.06
    Bind
    -0.06
    別
    -0.06
    אל
    -0.06
    .pre
    -0.06
     müşter
    -0.06
    	level
    -0.06
    ام
    -0.06
    POSITIVE LOGITS
    charging
    0.07
    董事会
    0.07
    위원회
    0.07
    多方
    0.07
    SET
    0.07
    稀
    0.07
    lings
    0.07
    0.07
     personal
    0.06
     scramble
    0.06
    Act Density 0.021%

    No Known Activations