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

    Neuronpedia

    INDEX
    Explanations

    import render

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是非
    0.76
    ዋ
    0.74
    女朋友
    0.69
     اک
    0.66
     Nicht
    0.64
     א
    0.64
    eram
    0.64
    ত্যা
    0.63
    ㄦ
    0.62
     طبی
    0.62
    POSITIVE LOGITS
    带来了
    0.89
    带来
    0.86
     qualities
    0.84
    帶來
    0.83
    ស្ថាន
    0.81
     Thế
    0.79
    Mapped
    0.74
     strokeWeight
    0.74
    ”]
    0.73
     maps
    0.73
    Act Density 0.000%

    No Known Activations