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

    Neuronpedia

    INDEX
    Explanations

    user preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    agon
    0.43
    wr
    0.39
    ango
    0.35
    ける
    0.35
    ँकि
    0.35
     assolutamente
    0.35
    Sh
    0.34
    ாம்
    0.34
    Alien
    0.34
     विराम
    0.34
    POSITIVE LOGITS
     FT
    0.42
     UA
    0.39
    }?
    0.39
     ইউজ
    0.39
    ゲル
    0.39
    CDATA
    0.38
     IUE
    0.38
     सीजी
    0.38
     FTC
    0.37
     geranium
    0.37
    Act Density 0.001%

    No Known Activations