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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, especially names of individuals involved in legal or notable events

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

    names and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Maren
    -0.41
     Игорь
    -0.35
     پست
    -0.34
    姨
    -0.34
     Thiago
    -0.33
     Юрий
    -0.32
    ografija
    -0.32
     hostile
    -0.32
    COUVER
    -0.32
    Иван
    -0.31
    POSITIVE LOGITS
    ftagPool
    0.79
     Meksiku
    0.61
     autorytatywna
    0.59
     disambiguazione
    0.59
    Océ
    0.57
     Houſe
    0.56
    ValueStyle
    0.55
     houſe
    0.55
    InteropServices
    0.54
     HasFactory
    0.54
    Act Density 0.571%

    No Known Activations