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

    Neuronpedia

    INDEX
    Explanations

    Java

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    城市
    -0.06
     fellowship
    -0.06
     towns
    -0.06
    <Link
    -0.06
     Аль
    -0.06
    962
    -0.06
    сти
    -0.06
    mess
    -0.06
    ası
    -0.05
     District
    -0.05
    POSITIVE LOGITS
     diverted
    0.07
     sonucunda
    0.06
     daily
    0.06
    amma
    0.06
     OE
    0.06
    .StackTrace
    0.06
     javascript
    0.06
    оля
    0.06
    rava
    0.06
     wast
    0.06
    Act Density 0.015%

    No Known Activations