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

    Neuronpedia

    INDEX
    Explanations

    News/product descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulet
    -0.07
    若干
    -0.07
    方方面面
    -0.06
    的大
    -0.06
    🦄
    -0.06
     assass
    -0.06
     تس
    -0.06
    ございます
    -0.06
    Coordinates
    -0.06
    身上
    -0.06
    POSITIVE LOGITS
     (![
    0.08
     packing
    0.07
    纥
    0.07
    FIELD
    0.07
     برنامج
    0.07
    (program
    0.07
     wś
    0.07
    phe
    0.07
     semantics
    0.07
    ghest
    0.06
    Act Density 0.217%

    No Known Activations