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

    Neuronpedia

    INDEX
    Explanations

    six-word story or summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    0.83
    m
    0.74
    y
    0.73
    n
    0.70
    f
    0.68
     Tsai
    0.67
    t
    0.67
    ing
    0.66
    ম
    0.64
    ar
    0.64
    POSITIVE LOGITS
    ियों
    0.79
    ﻧ
    0.69
    ﭼ
    0.67
     социа
    0.64
    ’
    0.63
    ва
    0.62
     giây
    0.59
    ﮔ
    0.58
     kontroller
    0.57
    <h4>
    0.57
    Act Density 0.000%

    No Known Activations