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

    Neuronpedia

    INDEX
    Explanations

    received

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (header
    -0.08
     offsetX
    -0.07
    汋
    -0.07
    高等院校
    -0.07
    奖学
    -0.07
    	bs
    -0.06
    на
    -0.06
    冒
    -0.06
    (using
    -0.06
    "H
    -0.06
    POSITIVE LOGITS
    镯
    0.07
     Loot
    0.07
    纠
    0.07
     ASIC
    0.06
    앴
    0.06
     cause
    0.06
     McC
    0.06
     week
    0.06
     ROC
    0.06
    Counts
    0.06
    Act Density 0.002%

    No Known Activations