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

    Neuronpedia

    INDEX
    Explanations

    code, data tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    젝
    -0.06
    surf
    -0.06
    $s
    -0.06
     Swan
    -0.06
     Dani
    -0.06
    άλ
    -0.06
    舗
    -0.06
    Dani
    -0.06
     MONEY
    -0.06
    atabases
    -0.05
    POSITIVE LOGITS
     midnight
    0.07
    .Invalid
    0.07
    _foot
    0.06
    方面
    0.06
     Záp
    0.06
    ाजस
    0.06
    [data
    0.06
     ymin
    0.06
     armed
    0.06
     Garcia
    0.06
    Act Density 0.025%

    No Known Activations