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

    Neuronpedia

    INDEX
    Explanations

    Inventions and patents

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    General
    0.45
     Gore
    0.43
     General
    0.42
    ME
    0.42
    Mead
    0.41
     WI
    0.40
    WI
    0.40
    general
    0.40
     Century
    0.40
     Carn
    0.40
    POSITIVE LOGITS
     k
    0.57
     к
    0.55
     basic
    0.46
     common
    0.42
    基本
    0.42
    基本的
    0.40
     básica
    0.38
     ke
    0.38
     till
    0.38
     oars
    0.37
    Act Density 0.000%

    No Known Activations