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

    Neuronpedia

    INDEX
    Explanations

    code and timestamps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avent
    -0.07
    .mouse
    -0.07
    CW
    -0.06
     mour
    -0.06
     Prints
    -0.06
     Axes
    -0.06
    rection
    -0.06
    dates
    -0.06
    いつ
    -0.06
     赤
    -0.06
    POSITIVE LOGITS
    .ptr
    0.07
    руб
    0.06
    ούς
    0.06
    不好
    0.06
    ्प
    0.06
    wdx
    0.06
     misunderstood
    0.06
    endencies
    0.06
    .help
    0.06
     introduced
    0.06
    Act Density 0.043%

    No Known Activations