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

    Neuronpedia

    INDEX
    Explanations

    words starting with Hel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    漫
    0.43
    赶
    0.39
     πάντα
    0.37
     लेकर
    0.35
    ウス
    0.35
    หาย
    0.35
    рованная
    0.35
     acabado
    0.35
    纳入
    0.35
    ندن
    0.34
    POSITIVE LOGITS
     HEL
    0.60
    HEL
    0.58
    Hel
    0.57
     Hel
    0.56
     hel
    0.55
    ヘル
    0.55
     helic
    0.54
    hel
    0.53
    헬
    0.53
     हेल
    0.52
    Act Density 0.023%

    No Known Activations