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

    Neuronpedia

    INDEX
    Explanations

    patterns related to coding or programming elements in text

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

    Followed by lowercase letters

    np_acts-logits-general · gemini-2.0-flash

    Thm, otf, asv

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.68
     الحره
    -0.65
    GEBURTSDATUM
    -0.64
     lenker
    -0.63
    KK
    -0.63
    DropTable
    -0.62
    Datuak
    -0.61
    はじめに
    -0.59
    RR
    -0.58
    QQ
    -0.57
    POSITIVE LOGITS
    h
    0.80
    g
    0.76
    b
    0.74
    c
    0.73
    y
    0.72
    f
    0.71
    z
    0.70
    u
    0.69
    r
    0.69
    m
    0.69
    Act Density 0.465%

    No Known Activations