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

    Neuronpedia

    INDEX
    Explanations

    numeric values and percentage representations

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

    Tokens followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    special codes and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rüyada
    -0.59
     ModelExpression
    -0.55
    Nederlands
    -0.51
    flashdata
    -0.50
     hữu
    -0.48
    Sommaire
    -0.47
    Fordítás
    -0.47
    theless
    -0.47
    ưới
    -0.46
    UnifiedTopology
    -0.46
    POSITIVE LOGITS
    cshtml
    0.61
     cherchés
    0.61
    oa̍t
    0.57
    #+#
    0.56
     worse
    0.52
    rungsseite
    0.51
    Cyfeiriadau
    0.51
    elashes
    0.50
    SBATCH
    0.50
    例句
    0.50
    Act Density 0.142%

    No Known Activations