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

    Neuronpedia

    INDEX
    Explanations

    numeric representations and descriptions of quantity

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

    Numbers four, five, six, eight, or two

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.83
     <=",
    -0.81
     Theſe
    -0.78
     ddelweddau
    -0.78
     houſe
    -0.75
     discography
    -0.74
     chrétiens
    -0.74
     purpoſe
    -0.74
     CreateTagHelper
    -0.73
     للمعارف
    -0.73
    POSITIVE LOGITS
     different
    1.04
    teen
    0.89
     separate
    0.88
     distinct
    0.86
    0
    0.81
    zehn
    0.76
     more
    0.72
    TEEN
    0.72
     large
    0.72
     total
    0.71
    Act Density 0.618%

    No Known Activations