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

    Neuronpedia

    INDEX
    Explanations

    sequences indicating a list or items in hierarchical format

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

    the word "Below"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Xna
    -0.47
    pmc
    -0.46
    huy
    -0.45
    rdi
    -0.44
    uran
    -0.44
     Flock
    -0.43
     Niro
    -0.42
     disambiguazione
    -0.42
    oopy
    -0.42
    OptionsMenu
    -0.42
    POSITIVE LOGITS
    Below
    1.33
     Below
    1.23
    Above
    0.80
    below
    0.76
     BELOW
    0.74
     Above
    0.71
     below
    0.70
    Berikut
    0.69
     Berikut
    0.63
     abaixo
    0.63
    Act Density 0.008%

    No Known Activations