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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eng
    -0.07
     outra
    -0.07
    "path
    -0.07
    agg
    -0.07
     בכל
    -0.07
     air
    -0.07
    ﻷ
    -0.07
    ادة
    -0.07
    placer
    -0.07
    逃脱
    -0.07
    POSITIVE LOGITS
    jid
    0.08
    composer
    0.07
    .sd
    0.07
     comedian
    0.07
    _rewrite
    0.07
    _lift
    0.07
     gratuite
    0.07
    donnees
    0.07
    caption
    0.07
     Gon
    0.06
    Act Density 0.001%

    No Known Activations