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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references to statistical metrics

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

    the number 9

    np_acts-logits-general · gemini-2.0-flash

    numbers like 9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seventeenth
    -1.14
     Sixth
    -1.07
     Seventeen
    -1.07
     sixteenth
    -1.06
     seventies
    -1.04
     sixth
    -1.03
     thirteenth
    -1.02
     Seventeenth
    -1.02
     Sixty
    -1.02
     sixties
    -1.00
    POSITIVE LOGITS
    9
    0.60
    loài
    0.43
    actionBar
    0.41
    <0xAA>
    0.41
    той
    0.41
     Cody
    0.41
     dépos
    0.41
     Centrale
    0.40
     élevées
    0.40
    وق
    0.40
    Act Density 0.586%

    No Known Activations