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

    Neuronpedia

    INDEX
    Explanations

    year count

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ι
    0.75
     convertir
    0.73
     βα
    0.70
     Pract
    0.68
     অমিত
    0.68
    ઢી
    0.66
    C
    0.66
    R
    0.66
    BROOK
    0.65
     вда
    0.65
    POSITIVE LOGITS
    ból
    0.77
    ങ്ങി
    0.75
     Совет
    0.74
     চলিয়া
    0.74
    ﻝ
    0.73
    சிரியர்
    0.73
     operacional
    0.73
     supervisory
    0.72
     Albums
    0.72
    সেল
    0.71
    Act Density 0.001%

    No Known Activations