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

    Neuronpedia

    INDEX
    Explanations

    library

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    የ
    -0.08
    (Collection
    -0.07
    licensed
    -0.07
    liers
    -0.07
    不管你
    -0.07
    baseline
    -0.07
    processing
    -0.07
    SAME
    -0.06
    	LOG
    -0.06
    法定
    -0.06
    POSITIVE LOGITS
    与此同时
    0.07
     trong
    0.07
    实施方案
    0.07
     سيكون
    0.07
    ⌋
    0.07
    .snap
    0.07
    になっている
    0.07
     orchestrated
    0.07
     suggests
    0.06
    []
    0.06
    Act Density 0.001%

    No Known Activations