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

    Neuronpedia

    INDEX
    Explanations

    neuro + word or suffix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۹
    2.08
    aya
    1.95
    ரது
    1.91
    ۲
    1.88
    ama
    1.76
    ۳
    1.76
    ানো
    1.74
    ána
    1.74
    ing
    1.72
    anın
    1.70
    POSITIVE LOGITS
    특별시
    2.53
    s
    2.41
    tanto
    2.19
     prostaglandins
    2.19
    n
    2.17
    ی
    2.14
    ्स
    2.06
    sels
    2.02
    t
    2.00
    ます
    1.98
    Act Density 0.003%

    No Known Activations