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

    Neuronpedia

    INDEX
    Explanations

    application

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﯮ
    -0.07
    .state
    -0.07
     cà
    -0.07
    <TSource
    -0.07
    .FLAG
    -0.07
    🦉
    -0.07
    蜂
    -0.07
    alta
    -0.06
     tout
    -0.06
    :-------------</
    -0.06
    POSITIVE LOGITS
     fury
    0.08
     sinister
    0.07
     gücü
    0.07
    ʅ
    0.07
    çiler
    0.07
    äche
    0.07
     mouths
    0.07
    broken
    0.06
    ürlich
    0.06
     drills
    0.06
    Act Density 0.001%

    No Known Activations