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

    Neuronpedia

    INDEX
    Explanations

    listing items or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clé
    0.42
    brano
    0.40
     fondamental
    0.40
    ய்டா
    0.39
    V
    0.38
     expérience
    0.38
    att
    0.38
    cuno
    0.37
    begin
    0.37
     avantages
    0.37
    POSITIVE LOGITS
     ට
    0.46
     pictures
    0.45
     Worcester
    0.44
     skaters
    0.43
    ﻄ
    0.43
    țională
    0.43
     skewers
    0.43
    氪
    0.43
     WPF
    0.43
     券
    0.42
    Act Density 0.000%

    No Known Activations