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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     came
    3.20
     of
    3.18
     arrives
    3.12
     featuring
    3.09
     including
    3.08
     using
    3.04
     historians
    3.02
     leaving
    2.96
     reveals
    2.93
     reckons
    2.90
    POSITIVE LOGITS
    7
    1.19
    rinsic
    1.08
    8
    0.94
    uruan
    0.94
    6
    0.93
     Nuss
    0.91
    pekte
    0.84
     존재
    0.82
     şeyler
    0.82
    3
    0.80
    Act Density 0.029%

    No Known Activations