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

    Neuronpedia

    INDEX
    Explanations

    top quark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coordinates
    -0.07
    ク
    -0.07
    ehen
    -0.07
     commissions
    -0.06
    ären
    -0.06
    Card
    -0.06
    afa
    -0.06
    lover
    -0.06
     ıs
    -0.06
    _modes
    -0.06
    POSITIVE LOGITS
     Syria
    0.06
     Detroit
    0.06
     JIT
    0.06
    0.06
    تامبر
    0.06
    ButtonDown
    0.06
    (nc
    0.06
    RootElement
    0.06
     bardzo
    0.06
     都
    0.05
    Act Density 0.003%

    No Known Activations