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

    Neuronpedia

    INDEX
    Explanations

    articles and comparative phrases

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

    more than a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.47
    oneofs
    -0.47
    encodeWith
    -0.42
    Referències
    -0.41
    sendLogPayload
    -0.41
     istrinya
    -0.41
     aguja
    -0.40
     оригіналу
    -0.38
     auprès
    -0.38
     something
    -0.38
    POSITIVE LOGITS
     Walkover
    0.50
     MenuView
    0.48
    side
    0.45
    cul
    0.44
    ﷺ
    0.43
     fide
    0.43
    hup
    0.42
     Fuk
    0.42
    <bos>
    0.42
    ibo
    0.42
    Act Density 0.021%

    No Known Activations