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

    Neuronpedia

    INDEX
    Explanations

    LaTeX package and document setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Consulting
    0.83
     barric
    0.83
     Forecast
    0.82
     Cardio
    0.81
     rigid
    0.80
     QB
    0.78
     coax
    0.77
     Watergate
    0.77
     BOX
    0.77
     peek
    0.76
    POSITIVE LOGITS
    usepackage
    1.28
    define
    1.02
    uset
    0.85
    Declare
    0.79
    title
    0.78
    begin
    0.76
    declare
    0.70
    Require
    0.68
    capt
    0.68
    Define
    0.67
    Act Density 0.010%

    No Known Activations