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

    Neuronpedia

    INDEX
    Explanations

    calls to action or imperative statements

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

    check out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.55
    ✭✭
    -0.54
    Искәрмәләр
    -0.54
    rungsseite
    -0.53
    TagMode
    -0.51
    contentLoaded
    -0.51
     Biôgrafia
    -0.46
     <=",
    -0.46
     publicitaires
    -0.46
    cstdio
    -0.45
    POSITIVE LOGITS
     Einf
    0.37
     inspired
    0.37
     envol
    0.37
     has
    0.36
    pret
    0.36
    Referencies
    0.36
    melis
    0.36
     Choose
    0.35
     using
    0.35
    wrap
    0.35
    Act Density 0.238%

    No Known Activations