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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     puzzled
    -0.07
    星
    -0.06
    属性
    -0.06
    "](
    -0.06
     immature
    -0.06
     concede
    -0.06
    เกาะ
    -0.06
    зь
    -0.06
    fout
    -0.06
    loating
    -0.06
    POSITIVE LOGITS
     μας
    0.06
    alyzer
    0.06
    'une
    0.06
     accom
    0.06
    ्बन
    0.06
     laden
    0.06
     entity
    0.06
    .flatMap
    0.06
     lon
    0.06
     ranged
    0.05
    Act Density 0.006%

    No Known Activations