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

    Neuronpedia

    INDEX
    Explanations

    physical awareness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urètre
    0.52
    Ｆ
    0.52
    Ꮈ
    0.49
    elwv
    0.48
    ExposureTime
    0.48
     piety
    0.47
     pious
    0.46
     контроли
    0.46
    ꔹ
    0.46
    ཥ
    0.45
    POSITIVE LOGITS
    ,
    0.61
     by
    0.51
    :
    0.46
     Bar
    0.46
     ar
    0.45
     bar
    0.44
     tín
    0.44
    '
    0.43
     and
    0.43
    [
    0.43
    Act Density 0.002%

    No Known Activations