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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gold
    -0.08
     gold
    -0.08
    _gold
    -0.07
    authority
    -0.07
    .schemas
    -0.07
     synthesis
    -0.07
     Hair
    -0.07
     sintet
    -0.07
    Gold
    -0.07
    [attr
    -0.07
    POSITIVE LOGITS
     عنها
    0.09
     Spears
    0.08
     terlebih
    0.08
     установлен
    0.08
    惠
    0.07
     исполн
    0.07
    روب
    0.07
     виб
    0.07
     ее
    0.07
    llllllll
    0.07
    Act Density 0.072%

    No Known Activations