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

    Neuronpedia

    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .FileOutputStream
    -0.07
    oralType
    -0.07
    Bearer
    -0.06
     LoggerFactory
    -0.06
     goofy
    -0.06
    のような
    -0.06
    /Branch
    -0.06
     Dickinson
    -0.06
    Mixin
    -0.06
    diler
    -0.06
    POSITIVE LOGITS
    표
    0.07
    Super
    0.06
    avaş
    0.06
    ATES
    0.06
    	block
    0.06
    .xaml
    0.06
    _prime
    0.06
     объект
    0.06
     Firm
    0.06
    .Sample
    0.06
    Act Density 0.006%

    No Known Activations