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

    Neuronpedia

    INDEX
    Explanations

    numerical values and references in the text

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

    Numbers within lists

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     henvisninger
    -0.59
    ebbe
    -0.50
    MLLoader
    -0.49
     مشين
    -0.49
    rd
    -0.48
    hpur
    -0.47
    fxml
    -0.47
     ber
    -0.46
     متعلقه
    -0.46
    Hozzáférés
    -0.46
    POSITIVE LOGITS
    ſelves
    0.72
     Majefty
    0.71
     houſe
    0.70
     Monfieur
    0.70
    FormTagHelper
    0.70
     Diſ
    0.67
     Conſ
    0.67
     Reſ
    0.66
     Pyrr
    0.65
    ſelf
    0.65
    Act Density 0.104%

    No Known Activations