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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     известно
    -0.08
     가능합니다
    -0.08
    _LITERAL
    -0.08
     Schr
    -0.08
     существует
    -0.08
    czy
    -0.08
     sunshine
    -0.08
     لعب
    -0.08
     Nixon
    -0.07
     sebenarnya
    -0.07
    POSITIVE LOGITS
     শেষে
    0.10
     sonunda
    0.10
     culminating
    0.09
     akhirnya
    0.09
     summar
    0.08
     concluding
    0.08
    最後
    0.08
     importantly
    0.08
    まとめ
    0.08
     saranno
    0.08
    Act Density 0.032%

    No Known Activations