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

    Neuronpedia

    INDEX
    Explanations

    hydrated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Player
    -0.08
    .enemy
    -0.07
     kullanılan
    -0.07
     Pioneer
    -0.07
     SetValue
    -0.07
    orsche
    -0.07
    高手
    -0.07
    ương
    -0.07
    ӊ
    -0.07
     vaccine
    -0.07
    POSITIVE LOGITS
    positions
    0.07
    postgres
    0.07
    UNIT
    0.07
    豆瓣
    0.07
    上げ
    0.07
    端正
    0.07
    좃
    0.07
    Paragraph
    0.07
     succinct
    0.07
    (define
    0.06
    Act Density 0.006%

    No Known Activations