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

    Neuronpedia

    INDEX
    Explanations

    κ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _INLINE
    -0.07
     طور
    -0.07
    ','=',
    -0.06
     transformation
    -0.06
     데이터
    -0.06
    =L
    -0.06
    AZ
    -0.06
    (rx
    -0.06
            ↵        ↵        ↵
    -0.06
    YK
    -0.06
    POSITIVE LOGITS
     Took
    0.07
     Parkinson
    0.07
    ICATION
    0.07
     activating
    0.07
     robes
    0.06
    يكا
    0.06
     любой
    0.06
    üslüman
    0.06
    افته
    0.06
    报道
    0.06
    Act Density 0.003%

    No Known Activations