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

    Neuronpedia

    INDEX
    Explanations

    the occurrences of specific patterns or conditions related to behavior and semantics in text

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

    Following prepositions (of, by, into)

    np_acts-logits-general · gemini-2.0-flash

    French words and medical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    -0.57
    m
    -0.56
    de
    -0.55
    r
    -0.53
    b
    -0.53
    c
    -0.52
    f
    -0.52
    p
    -0.52
    v
    -0.51
    co
    -0.51
    POSITIVE LOGITS
     ainfi
    0.79
     enfans
    0.68
    IBLIO
    0.66
     traités
    0.64
     avoient
    0.63
     auroit
    0.62
     fidé
    0.62
     définiti
    0.62
     normaux
    0.61
     passés
    0.61
    Act Density 0.701%

    No Known Activations