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

    Neuronpedia

    INDEX
    Explanations

    prefer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    뭏
    -0.08
     наз
    -0.07
    setPosition
    -0.07
    :test
    -0.06
    /test
    -0.06
    __)↵
    -0.06
    קש
    -0.06
     appoint
    -0.06
    ⽇
    -0.06
    apixel
    -0.06
    POSITIVE LOGITS
    ibilidad
    0.07
     cuales
    0.07
    BA
    0.07
    有更多的
    0.07
    (&
    0.06
     (&
    0.06
    _pressure
    0.06
    (tab
    0.06
    這個
    0.06
     chống
    0.06
    Act Density 0.009%

    No Known Activations