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

    Neuronpedia

    INDEX
    Explanations

    ainer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    {text
    -0.09
    功力
    -0.07
    (transaction
    -0.07
    Motor
    -0.07
     cousins
    -0.07
    Immediately
    -0.07
    .getSession
    -0.07
    uated
    -0.06
     Room
    -0.06
    pletely
    -0.06
    POSITIVE LOGITS
    出演
    0.06
    𥻗
    0.06
    ﻔ
    0.06
    структур
    0.06
    плав
    0.06
    싣
    0.06
    牾
    0.06
     presidente
    0.06
     sqrt
    0.06
    깼
    0.06
    Act Density 0.002%

    No Known Activations