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

    Neuronpedia

    INDEX
    Explanations

    web/net

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     royal
    -0.08
    nelles
    -0.07
     проводят
    -0.07
     đặt
    -0.07
     interdum
    -0.07
    .Operation
    -0.07
    Italian
    -0.07
     �
    -0.07
     дода
    -0.07
     בין
    -0.07
    POSITIVE LOGITS
     schlafen
    0.09
     darknet
    0.09
     blockchain
    0.08
     criminals
    0.08
     phishing
    0.08
    ဲ
    0.08
    nich
    0.08
    恐
    0.08
     cryptocurrencies
    0.08
     �
    0.07
    Act Density 0.003%

    No Known Activations