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

    Neuronpedia

    INDEX
    Explanations

    xhtml, publications, clitoris

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    1.02
    ik
    0.92
     It
    0.77
     athleticism
    0.76
    س
    0.74
     राशि
    0.71
    k
    0.70
    vature
    0.69
    him
    0.68
    ter
    0.66
    POSITIVE LOGITS
    ↵↵
    1.06
     by
    1.03
    是
    1.01
    ↵
    0.96
    Б
    0.89
     في
    0.87
    ৫
    0.87
    ה
    0.84
    는
    0.83
    Ста
    0.80
    Act Density 0.007%

    No Known Activations