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

    Neuronpedia

    INDEX
    Explanations

    Google Image search URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sax
    0.41
     sacré
    0.39
    നായ
    0.38
    সরকারী
    0.37
    Са
    0.37
     Mab
    0.37
    查詢
    0.36
     Sa
    0.36
    witch
    0.36
    बा
    0.34
    POSITIVE LOGITS
     Artículo
    0.40
     tanh
    0.38
    ❼
    0.37
     ssh
    0.36
    סת
    0.36
    Figs
    0.35
     алуу
    0.35
     मृतक
    0.35
     redir
    0.35
     отде
    0.34
    Act Density 0.002%

    No Known Activations