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

    Neuronpedia

    INDEX
    Explanations

    derivative calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >Total
    -0.07
    dığı
    -0.07
    油画
    -0.07
    鲞
    -0.07
    绣
    -0.07
    星座
    -0.07
    	n
    -0.07
    绾
    -0.07
     tranny
    -0.06
     INF
    -0.06
    POSITIVE LOGITS
    arendra
    0.07
    istical
    0.07
    Endpoint
    0.07
    .generic
    0.07
    四处
    0.07
    ETA
    0.07
    市场主体
    0.06
    .routes
    0.06
    /scripts
    0.06
    azo
    0.06
    Act Density 0.005%

    No Known Activations