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

    Neuronpedia

    INDEX
    Explanations

    in addition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jenigen
    0.46
    elő
    0.42
    aldehyde
    0.42
    ➢
    0.41
     få
    0.41
     Dadurch
    0.41
    ла
    0.40
    ^{
    0.40
    ка
    0.39
     Änderungen
    0.38
    POSITIVE LOGITS
     ablaze
    0.51
    માં
    0.51
    schild
    0.50
     rampant
    0.50
    ک
    0.49
     levied
    0.49
    ৌজ
    0.47
    ዳል
    0.47
     encompassed
    0.47
    mik
    0.47
    Act Density 0.163%

    No Known Activations