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

    Neuronpedia

    INDEX
    Explanations

    marker tokens in the text

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

    Follows "Q:" or contains non-English words

    np_acts-logits-general · gemini-2.0-flash

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ã
    -0.58
    amc
    -0.51
    Ther
    -0.51
    rungsseite
    -0.50
    zał
    -0.49
    Â
    -0.48
    theo
    -0.47
    yz
    -0.47
    rc
    -0.46
    ´
    -0.46
    POSITIVE LOGITS
     فريبيس
    0.67
     tiegħ
    0.63
     opportunità
    0.61
    berdayakan
    0.61
     affari
    0.59
     bénévoles
    0.58
     grève
    0.58
     étoient
    0.58
     tendenza
    0.57
    SourceChecksum
    0.57
    Act Density 0.009%

    No Known Activations