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

    Neuronpedia

    INDEX
    Explanations

    sequences and patterns in numerical data or arrays

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

    The number six

    np_acts-logits-general · gemini-2.0-flash

    the number six

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Atoi
    -0.63
     György
    -0.56
    Itoa
    -0.54
    <?
    -0.48
    ǎ
    -0.48
    ../../
    -0.47
     Charity
    -0.46
     yana
    -0.46
     Haig
    -0.46
    zur
    -0.45
    POSITIVE LOGITS
    6
    1.67
     Sixth
    1.35
     sixth
    1.32
     Six
    1.31
     six
    1.29
     SIX
    1.22
    six
    1.20
    Sixth
    1.14
    六
    1.12
    Six
    1.11
    Act Density 0.689%

    No Known Activations