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

    Neuronpedia

    INDEX
    Explanations

    words that denote summation and mathematical operations

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

    ending in "m", "r", or "l"

    np_acts-logits-general · gemini-2.0-flash

    cardiac and chemical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    -1.09
    u
    -1.07
    at
    -1.05
    in
    -1.04
    is
    -0.99
    r
    -0.98
    c
    -0.97
    as
    -0.95
    an
    -0.94
    n
    -0.93
    POSITIVE LOGITS
    Hauptartikel
    0.69
    WriteTagHelper
    0.63
     iprot
    0.63
     Normdatei
    0.63
    adecimal
    0.61
    0.59
     تضيفلها
    0.59
     surla
    0.58
     Administrativna
    0.58
     дописавши
    0.57
    Act Density 0.341%

    No Known Activations