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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    違う
    -0.08
     thế
    -0.07
     hiểu
    -0.07
    frared
    -0.07
     Wien
    -0.07
    �
    -0.07
    粲
    -0.07
    ڕ
    -0.07
     æ
    -0.07
    Immutable
    -0.07
    POSITIVE LOGITS
    给你们
    0.09
    ounters
    0.08
    olución
    0.08
    FTA
    0.08
    不便
    0.07
     Cutting
    0.07
    cimiento
    0.07
    테
    0.07
    ورو
    0.07
     severed
    0.07
    Act Density 0.002%

    No Known Activations