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

    Neuronpedia

    INDEX
    Explanations

    words indicating certainty or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    adverbs of certainty and sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    -0.52
    NullCheck
    -0.51
     يتيمه
    -0.45
    RunWith
    -0.45
    مصادر
    -0.45
    FLU
    -0.44
    GeneratedValue
    -0.43
     nahilalakip
    -0.43
     Rued
    -0.42
    Λ
    -0.42
    POSITIVE LOGITS
     blevet
    0.76
     blitt
    0.65
     EconPapers
    0.54
     being
    0.53
     estão
    0.53
     mijne
    0.52
     becoming
    0.51
     blivit
    0.50
     mukana
    0.49
    Estou
    0.49
    Act Density 0.173%

    No Known Activations