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

    Neuronpedia

    INDEX
    Explanations

    80/20 rule

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المسلحة
    -0.07
     предусмотрен
    -0.07
     NL
    -0.07
     activated
    -0.06
    san
    -0.06
    reads
    -0.06
     RECEIVE
    -0.06
     Extremely
    -0.06
    after
    -0.06
     Found
    -0.06
    POSITIVE LOGITS
    要去
    0.07
    蜂蜜
    0.07
    Bear
    0.07
    ⁿ
    0.07
    poi
    0.07
     gps
    0.07
    .coords
    0.07
    酱油
    0.07
     gard
    0.06
     hypo
    0.06
    Act Density 0.005%

    No Known Activations