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

    Neuronpedia

    INDEX
    Explanations

    *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.24
    ش
    1.12
    ることができます
    1.08
    ія
    1.05
    uments
    1.01
    ният
    1.01
    may
    1.00
    ಬಹುದು
    1.00
    либо
    1.00
    可能性がある
    0.99
    POSITIVE LOGITS
     I
    1.30
     nervously
    1.23
    ರ್ಷ
    1.19
     пыта
    1.16
     intravenously
    1.16
     equator
    1.14
     حبايبي
    1.13
     pequeña
    1.13
     aliphatic
    1.10
     очередной
    1.09
    Act Density 0.234%

    No Known Activations