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

    Neuronpedia

    INDEX
    Explanations

    how something moves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    莫
    0.44
     synergies
    0.40
     ਵਿ
    0.39
    傗
    0.39
     digo
    0.39
    ｉ
    0.39
     Owing
    0.38
    いた
    0.38
     ó
    0.37
    炜
    0.37
    POSITIVE LOGITS
    NCc
    0.39
    …………………………………………
    0.38
    hte
    0.37
    潾
    0.36
    ماية
    0.35
     cobra
    0.35
    php
    0.35
    ippy
    0.34
     leaning
    0.34
    pendicular
    0.33
    Act Density 0.000%

    No Known Activations