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

    Neuronpedia

    INDEX
    Explanations

    true

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tích
    -0.07
    otence
    -0.07
     NSStringFromClass
    -0.07
    扃
    -0.07
     List
    -0.06
    .inst
    -0.06
    .props
    -0.06
    ㎿
    -0.06
     Sew
    -0.06
    否定
    -0.06
    POSITIVE LOGITS
     algebra
    0.07
     ايضا
    0.07
    토
    0.06
     slippery
    0.06
    生命
    0.06
     rebuild
    0.06
    -end
    0.06
    .toUpperCase
    0.06
    (random
    0.06
    炟
    0.06
    Act Density 0.030%

    No Known Activations