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

    Neuronpedia

    INDEX
    Explanations

    names and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.23
     lekin
    0.20
     instagram
    0.20
     doesn
    0.20
     latter
    0.19
     info
    0.19
     php
    0.19
     first
    0.19
    ");
    0.19
     bhfu
    0.19
    POSITIVE LOGITS
    佉
    0.20
     Johnston
    0.20
    များ
    0.20
     молеку
    0.20
    physiological
    0.20
    PLASMA
    0.20
     McColl
    0.19
    欬
    0.19
     Weir
    0.19
    硣
    0.19
    Act Density 0.012%

    No Known Activations