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

    Neuronpedia

    INDEX
    Explanations

    numerical values or quantities

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

    numbers followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.51
     AspNetCore
    -0.49
    govina
    -0.47
    bcryptjs
    -0.47
    Werdegang
    -0.45
    MigrationBuilder
    -0.45
    aarrggbb
    -0.43
    áctenos
    -0.42
    featureID
    -0.42
    IntoConstraints
    -0.41
    POSITIVE LOGITS
    Five
    0.46
    Two
    0.45
    Six
    0.44
    ếng
    0.43
    Few
    0.42
    Four
    0.41
    Juan
    0.40
    Vorlage
    0.40
    Thirty
    0.40
    retweeted
    0.40
    Act Density 0.024%

    No Known Activations