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

    Neuronpedia

    INDEX
    Explanations

    inherent heart tell Require determines feeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    L
    1.18
    ется
    1.13
    ே
    1.12
    T
    1.12
    est
    1.10
    C
    1.06
     रवाना
    1.03
    entrySet
    1.03
     sprung
    1.00
    ैम
    0.99
    POSITIVE LOGITS
     přev
    1.39
    ̔
    1.30
    treas
    1.27
    stimulated
    1.24
     upas
    1.22
    reed
    1.22
    शुदा
    1.20
    किशोर
    1.19
    িবদ্ধ
    1.17
    没想到
    1.16
    Act Density 0.000%

    No Known Activations