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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .GetData
    -0.07
    ۆ
    -0.07
    (primary
    -0.07
     chế
    -0.07
    ceptions
    -0.07
    清算
    -0.06
    слов
    -0.06
    ﮅ
    -0.06
    暧
    -0.06
    ⊰
    -0.06
    POSITIVE LOGITS
     Always
    0.08
    Manufacturer
    0.07
     Researchers
    0.07
    redentials
    0.07
    智库
    0.07
    亲眼
    0.07
    :k
    0.07
     Bib
    0.07
    game
    0.06
    ratulations
    0.06
    Act Density 0.075%

    No Known Activations