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

    Neuronpedia

    INDEX
    Explanations

    inline or react with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    િસ
    0.49
    B
    0.48
     usare
    0.48
     using
    0.48
    屋さん
    0.47
    H
    0.46
     relying
    0.45
    yas
    0.44
     Conan
    0.44
    FIGURE
    0.44
    POSITIVE LOGITS
     새로운
    0.43
     끊
    0.43
     급
    0.41
    를
    0.41
     디
    0.39
     하여
    0.39
     인해
    0.39
     접
    0.37
     반
    0.36
     데
    0.36
    Act Density 0.001%

    No Known Activations