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

    Neuronpedia

    INDEX
    Explanations

    numbers and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    তুন
    0.46
    Се
    0.43
    异步
    0.43
     మె
    0.41
     lull
    0.41
    東
    0.40
    旸
    0.38
    短暂
    0.37
    水印
    0.37
    东
    0.37
    POSITIVE LOGITS
    a
    0.51
    redi
    0.48
    achusetts
    0.45
     policial
    0.44
    hrs
    0.43
    police
    0.42
     sanguí
    0.42
    ﻟ
    0.41
     becom
    0.41
    ራል
    0.40
    Act Density 0.002%

    No Known Activations