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

    Neuronpedia

    INDEX
    Explanations

    different types and kinds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dlatego
    1.07
     Hương
    1.04
    1
    1.04
    な
    0.95
    س
    0.93
    こともある
    0.92
    なる
    0.92
    в
    0.91
    رسٹ
    0.90
    larının
    0.90
    POSITIVE LOGITS
    ième
    1.38
    arono
    1.18
     nedenle
    1.16
    ى
    1.14
     считать
    1.11
    ங்கிணை
    1.10
    ㅎㅎ
    1.09
     criou
    1.09
    𝕒
    1.08
    ية
    1.07
    Act Density 0.081%

    No Known Activations