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

    Neuronpedia

    INDEX
    Explanations

    Repeated numeric values and mathematical expressions

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

    The number six or related ordinal forms

    np_acts-logits-general · gemini-2.0-flash

    six followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     György
    -0.67
     disambiguazione
    -0.63
    اض
    -0.56
     Hartley
    -0.54
     Charity
    -0.54
    Atoi
    -0.54
     Acorn
    -0.53
     charcoal
    -0.53
     Authority
    -0.52
     fifteenth
    -0.52
    POSITIVE LOGITS
    6
    1.69
     Sixth
    1.35
     sixth
    1.31
     Six
    1.25
     six
    1.19
     SIX
    1.17
    six
    1.13
    Sixth
    1.10
    sixth
    1.10
    ６
    1.09
    Act Density 0.478%

    No Known Activations