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

    Neuronpedia

    INDEX
    Explanations

    the preposition "from" indicating sources or origins

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

    ranging from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arşivlendi
    -0.47
    BagLayout
    -0.39
    <0xEA>
    -0.36
     consecu
    -0.32
    Manbalar
    -0.30
    GAC
    -0.30
    KEYCODE
    -0.30
     because
    -0.30
    con
    -0.28
    Con
    -0.28
    POSITIVE LOGITS
     zwiſchen
    0.68
    <unused41>
    0.68
    <unused74>
    0.67
    <unused8>
    0.67
    <unused51>
    0.67
    <unused43>
    0.67
    <unused79>
    0.67
    <unused28>
    0.67
    <unused14>
    0.67
    <unused16>
    0.67
    Act Density 0.013%

    No Known Activations