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

    Neuronpedia

    INDEX
    Explanations

    words ending in y or ergy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ivity
    0.68
    speople
    0.66
    swith
    0.59
    ानंतर
    0.59
    ामध्ये
    0.57
    LY
    0.53
    ాన్ని
    0.52
    IVITY
    0.51
    ामुळे
    0.51
    ssss
    0.49
    POSITIVE LOGITS
    yyyy
    0.88
    yyyyyyyy
    0.88
    ுள்ளார்
    0.73
    yy
    0.72
    ுள்ளனர்
    0.64
    ء
    0.57
    ுள்ள
    0.55
    outube
    0.53
    й
    0.52
    ٰ
    0.52
    Act Density 0.458%

    No Known Activations