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

    Neuronpedia

    INDEX
    Explanations

    default values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    عا
    1.17
    姆
    1.14
    thood
    1.13
    洌
    1.10
    ции
    1.10
    偶
    1.08
    asures
    1.08
    ری
    1.05
    ių
    1.05
    ជ្ជ
    1.04
    POSITIVE LOGITS
    情况下
    1.38
     hyperactivity
    1.15
    값을
    1.14
    ivamente
    1.10
    값
    1.10
    값이
    1.09
    ively
    1.07
    +}\
    1.06
    वों
    1.06
     assume
    1.06
    Act Density 0.045%

    No Known Activations