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

    Neuronpedia

    INDEX
    Explanations

    here for you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    1.56
    o
    1.55
    ে
    1.42
    ी
    1.37
    a
    1.31
    er
    1.24
    ﺎ
    1.21
    ﻪ
    1.18
    橥
    1.17
    ו
    1.16
    POSITIVE LOGITS
     रहकर
    1.38
     मौजूद
    1.27
    𝐾
    1.17
     gesamten
    1.16
     fumes
    1.12
     folgenden
    1.10
     আছেন
    1.09
     रहते
    1.07
     effluents
    1.06
    𝙉
    1.05
    Act Density 0.087%

    No Known Activations