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

    Neuronpedia

    INDEX
    Explanations

    mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    decorators
    -0.07
     Ready
    -0.06
    …)↵↵
    -0.06
     [...]↵↵
    -0.06
     сет
    -0.06
    ی
    -0.06
    餐
    -0.06
     Bronze
    -0.06
    การพ
    -0.06
    _verify
    -0.06
    POSITIVE LOGITS
     Makes
    0.07
    linux
    0.07
    annotation
    0.07
    Atlas
    0.06
    485
    0.06
     meses
    0.06
    itate
    0.06
    成绩
    0.06
    wild
    0.06
     hateful
    0.06
    Act Density 0.004%

    No Known Activations