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

    Neuronpedia

    INDEX
    Explanations

    financial assessment and reading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )):
    0.45
    ാനുള്ള
    0.44
    (-\
    0.43
    RIX
    0.42
    HIT
    0.42
    ल्लभ
    0.42
    ([-
    0.41
    ≙
    0.41
    ೊಳ
    0.41
    )^{-
    0.41
    POSITIVE LOGITS
    '
    0.55
     unprecedented
    0.53
     carte
    0.50
     geek
    0.49
     unparalleled
    0.48
     ਵਿੱਚ
    0.48
     côté
    0.48
     nerfs
    0.48
     Northern
    0.47
     maw
    0.47
    Act Density 0.000%

    No Known Activations