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

    Neuronpedia

    INDEX
    Explanations

    R words and endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     steeped
    0.76
    rable
    0.71
     warp
    0.68
     visually
    0.68
     rec
    0.67
     headings
    0.67
     visual
    0.67
     waffle
    0.66
     textbook
    0.65
     HTTPS
    0.64
    POSITIVE LOGITS
    atios
    1.09
    hapsody
    1.03
    hythmic
    1.02
    henium
    1.00
    ushed
    1.00
    ationale
    0.99
    uminate
    0.96
    acional
    0.94
    acket
    0.92
    approche
    0.92
    Act Density 0.113%

    No Known Activations