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

    Neuronpedia

    INDEX
    Explanations

    numerical values and quantities

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

    numbers with decimal points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Houſe
    -0.75
     purpoſe
    -0.69
     houſe
    -0.68
     pleaſure
    -0.68
     Hitam
    -0.67
     Budaya
    -0.67
     camiset
    -0.66
     Irán
    -0.66
    ltä
    -0.65
    arangay
    -0.65
    POSITIVE LOGITS
    stdio
    0.44
    subsubsection
    0.42
    BagLayout
    0.40
    SourceChecksum
    0.39
     Worn
    0.39
    ----</
    0.35
    TextBoxColumn
    0.35
    >`;
    0.34
     */;
    0.34
    anius
    0.34
    Act Density 0.164%

    No Known Activations