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

    Neuronpedia

    INDEX
    Explanations

    words following 'the'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meno
    0.44
    )+\
    0.43
     zawsze
    0.42
    सोबत
    0.41
    வரை
    0.41
     televiz
    0.40
     を
    0.39
     memainkan
    0.39
    +](=
    0.38
    IIUM
    0.38
    POSITIVE LOGITS
    roweak
    0.48
    ారి
    0.46
     accrued
    0.45
    谊
    0.45
    ajari
    0.42
    冲击
    0.42
     appalled
    0.42
     दस्ते
    0.41
    cssMode
    0.41
    たら
    0.41
    Act Density 0.001%

    No Known Activations