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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of uncertainty

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

    "t" followed by a word indicating thought or knowledge

    np_acts-logits-general · gemini-2.0-flash

    don't know, don't believe, don't get

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     linkovi
    -0.37
    出版年
    -0.35
    rokken
    -0.33
     saurait
    -0.33
     trouvez
    -0.33
     fallu
    -0.32
     conveniente
    -0.32
     appena
    -0.32
    Bronnen
    -0.32
     ucapnya
    -0.32
    POSITIVE LOGITS
     informée
    0.60
    LEncoder
    0.53
    argout
    0.52
     Ahnung
    0.51
     know
    0.50
     KNOW
    0.50
    KNOW
    0.49
     فريبيس
    0.49
    Rohy
    0.49
     trăm
    0.49
    Act Density 0.331%

    No Known Activations