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

    Neuronpedia

    INDEX
    Explanations

    Affirmations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ality
    -0.07
    說
    -0.06
     wonders
    -0.06
     cautious
    -0.06
    ía
    -0.06
    ález
    -0.06
     материалов
    -0.06
    Req
    -0.06
     riff
    -0.06
    ordering
    -0.06
    POSITIVE LOGITS
    tableName
    0.07
    .—
    0.06
    .Sin
    0.06
     <",
    0.06
     sq
    0.06
     Ogre
    0.06
     mil
    0.06
    cate
    0.06
     Tar
    0.06
    ／/
    0.06
    Act Density 0.023%

    No Known Activations