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

    Neuronpedia

    INDEX
    Explanations

    Colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     müş
    -0.07
     has
    -0.07
    olland
    -0.07
     viện
    -0.07
    (hand
    -0.07
     owes
    -0.07
    (h
    -0.07
     тов
    -0.06
     Kart
    -0.06
     Angus
    -0.06
    POSITIVE LOGITS
     speeches
    0.07
     strr
    0.06
    κτή
    0.06
    ποι
    0.06
    .cleaned
    0.06
    ेकर
    0.06
    StackTrace
    0.06
    filtr
    0.06
    _Dec
    0.06
     sæ
    0.06
    Act Density 2.039%

    No Known Activations