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

    Neuronpedia

    INDEX
    Explanations

    symbols and characters commonly used in programming and mathematical expressions

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

    Mathematical or code expressions

    np_acts-logits-general · gemini-2.0-flash

    one, 1, or éen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forty
    -0.78
     fifty
    -0.71
     Forty
    -0.71
     sixty
    -0.71
     seventy
    -0.71
     thirty
    -0.70
     Sixty
    -0.69
     eighty
    -0.67
    forty
    -0.65
     Fifty
    -0.64
    POSITIVE LOGITS
    1
    1.40
    ۱
    0.93
     one
    0.90
    １
    0.90
     ONE
    0.84
     ۱
    0.82
     One
    0.77
     één
    0.77
    ONE
    0.71
    One
    0.71
    Act Density 1.279%

    No Known Activations