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

    Neuronpedia

    INDEX
    Explanations

    PHP coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SQ
    -0.08
     offend
    -0.07
     Dry
    -0.07
    igua
    -0.06
     specialized
    -0.06
    Forecast
    -0.06
    Acceleration
    -0.06
     Road
    -0.06
    Got
    -0.06
     niž
    -0.06
    POSITIVE LOGITS
    (run
    0.07
     Nelson
    0.06
    _PA
    0.06
    =email
    0.06
    :image
    0.06
     mercury
    0.06
    (il
    0.06
    .axes
    0.06
    ajaran
    0.06
    =password
    0.06
    Act Density 0.076%

    No Known Activations