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

    Neuronpedia

    INDEX
    Explanations

    eyelashes and lashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    0.91
    $,
    0.68
    $
    0.65
    $$\
    0.59
     it
    0.59
    σό
    0.58
    >
    0.58
    ，
    0.58
    idens
    0.57
     the
    0.56
    POSITIVE LOGITS
     lashes
    0.81
     on
    0.77
     eyelashes
    0.77
     revoc
    0.70
    ്ട
    0.69
    ್ರಿ
    0.69
    ৃত
    0.67
    师傅
    0.66
     écoles
    0.66
     ép
    0.64
    Act Density 0.002%

    No Known Activations