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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    frequency
    -0.07
    虑
    -0.07
    adder
    -0.07
     FORE
    -0.07
    vel
    -0.07
     glove
    -0.07
    快速
    -0.07
     intelligence
    -0.07
    憶
    -0.07
     return
    -0.07
    POSITIVE LOGITS
    صحف
    0.08
     pequ
    0.08
     المياه
    0.07
     לחל
    0.07
     gridColumn
    0.07
    NEW
    0.07
     getDescription
    0.07
    ▾
    0.07
     hari
    0.07
     כבר
    0.06
    Act Density 0.004%

    No Known Activations