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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     katı
    -0.07
    Segoe
    -0.07
    lobal
    -0.06
    hel
    -0.06
    Seats
    -0.06
    цями
    -0.06
    AMESPACE
    -0.06
     legitimacy
    -0.06
    [num
    -0.06
    ::~
    -0.06
    POSITIVE LOGITS
    ON
    0.09
     on
    0.08
    .Extensions
    0.08
    on
    0.07
     ON
    0.07
     onwards
    0.07
    发展
    0.06
    -progress
    0.06
     facts
    0.06
     karıştır
    0.06
    Act Density 0.020%

    No Known Activations