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

    Neuronpedia

    INDEX
    Explanations

    organic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    classification
    -0.07
    class
    -0.07
    Size
    -0.07
     onFocus
    -0.07
    Ṡ
    -0.07
    ContentSize
    -0.06
     oo
    -0.06
    뙤
    -0.06
    信用
    -0.06
    lü
    -0.06
    POSITIVE LOGITS
    医院
    0.08
    -layer
    0.07
    �
    0.07
    _secret
    0.07
    科学家
    0.07
    pline
    0.07
    갱
    0.07
    _partial
    0.07
     fashioned
    0.07
    your
    0.07
    Act Density 0.006%

    No Known Activations