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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and technical specifications

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

    list markers, bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ikusbot
    -0.84
     surla
    -0.82
     deſſen
    -0.82
     パンチラ
    -0.82
     $_(
    -0.81
    <unused41>
    -0.81
    <unused14>
    -0.80
    <unused51>
    -0.80
    <unused43>
    -0.80
    <unused8>
    -0.80
    POSITIVE LOGITS
    2
    0.33
    6
    0.30
    1
    0.29
    *
    0.29
     NSCoder
    0.28
    arraycopy
    0.28
    3
    0.28
    5
    0.28
    .
    0.28
    stackrel
    0.28
    Act Density 0.008%

    No Known Activations