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

    Neuronpedia

    INDEX
    Explanations

    references to digits and numerical representations

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

    digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Soares
    -0.49
     Rücks
    -0.46
     Rivas
    -0.46
     Kraus
    -0.45
    handleClose
    -0.44
     bará
    -0.44
     Erinnerungen
    -0.44
    aine
    -0.44
     unavoidable
    -0.44
    nados
    -0.43
    POSITIVE LOGITS
    Digit
    2.28
    digit
    2.27
     Digit
    2.23
     digit
    2.09
     DIGIT
    1.76
    DIGIT
    1.57
     digits
    1.13
     digitally
    1.11
     díg
    1.10
    Digi
    1.03
    Act Density 0.003%

    No Known Activations