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

    Neuronpedia

    INDEX
    Explanations

    numerical data and measurements

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

    Numbers or values

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by ordinal indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majefty
    -0.56
    cloudfront
    -0.56
     pleaſure
    -0.55
     ſtate
    -0.52
     Monfieur
    -0.49
     dext
    -0.49
     posterity
    -0.49
    RRect
    -0.48
     pleaf
    -0.47
     Reſ
    -0.47
    POSITIVE LOGITS
     earlier
    0.73
     précédente
    0.71
     Earlier
    0.64
    EDEFAULT
    0.64
    Earlier
    0.62
     précédentes
    0.61
     précédents
    0.61
     previous
    0.61
     sebelumnya
    0.61
    paravant
    0.61
    Act Density 1.262%

    No Known Activations