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

    Neuronpedia

    INDEX
    Explanations

    duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pouring
    -0.07
    直播
    -0.07
    Descending
    -0.07
    ://{
    -0.06
     monuments
    -0.06
     cosine
    -0.06
     numbering
    -0.06
    storybook
    -0.06
    Implement
    -0.06
     会
    -0.06
    POSITIVE LOGITS
     portfolio
    0.06
     uděl
    0.06
     Sox
    0.06
     đặt
    0.06
    กรรม
    0.06
     "^
    0.06
    ilin
    0.06
     CALC
    0.06
    ODO
    0.05
     MOS
    0.05
    Act Density 0.066%

    No Known Activations