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

    Neuronpedia

    INDEX
    Explanations

    percentages and measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igsaw
    -0.07
     gathers
    -0.07
     whose
    -0.06
     CD
    -0.06
     Lantern
    -0.06
     visibly
    -0.06
    ịp
    -0.06
    (fetch
    -0.06
    anggal
    -0.06
     adaptable
    -0.06
    POSITIVE LOGITS
    _PROD
    0.07
     fantas
    0.07
    用户名
    0.07
     غذ
    0.07
     každý
    0.06
    455
    0.06
    .toJson
    0.06
     curled
    0.06
    mailer
    0.06
     bö
    0.06
    Act Density 0.069%

    No Known Activations