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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ."↵↵↵↵
    -0.08
    。↵↵↵↵
    -0.07
    @Data
    -0.07
    -comments
    -0.07
     judicial
    -0.07
    큽
    -0.07
     учитыва
    -0.07
    /dialog
    -0.06
     Gill
    -0.06
     rises
    -0.06
    POSITIVE LOGITS
    ppe
    0.07
    ercicio
    0.07
    letic
    0.07
    战略
    0.07
    urahan
    0.06
    ır
    0.06
     ?:
    0.06
    [
    0.06
     gst
    0.06
    焓
    0.06
    Act Density 0.044%

    No Known Activations