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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PG
    -0.07
    	status
    -0.07
    ,Th
    -0.06
     chỉ
    -0.06
    	level
    -0.06
    خ
    -0.06
    uble
    -0.06
     conceptual
    -0.06
    .replace
    -0.06
    ymous
    -0.06
    POSITIVE LOGITS
     потер
    0.08
    爱吃
    0.07
     computers
    0.07
    的到来
    0.07
    טווח
    0.06
    _printer
    0.06
    fea
    0.06
    (tweet
    0.06
    它是
    0.06
    APP
    0.06
    Act Density 0.002%

    No Known Activations