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

    Neuronpedia

    INDEX
    Explanations

    sports scores, cobalt, paying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    佲
    0.48
     विशेषताएं
    0.47
     ?",
    0.46
    *,
    0.46
    십니까
    0.45
    ,*
    0.44
    되었
    0.43
    会不会
    0.43
    والفقار
    0.43
    Hawk
    0.43
    POSITIVE LOGITS
    視
    0.49
     P
    0.44
     гг
    0.43
     R
    0.42
    eneration
    0.42
    工事
    0.40
    alted
    0.40
    設定
    0.39
    Facades
    0.39
    lose
    0.39
    Act Density 0.002%

    No Known Activations