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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and chemical compound names

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

    Mathematical or scientific notation

    np_acts-logits-general · gemini-2.0-flash

    scientific units and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.98
    rungsseite
    -0.92
    setViewportView
    -0.91
    parsedMessage
    -0.90
    majánló
    -0.90
    <unused28>
    -0.86
    <unused3>
    -0.86
    <unused17>
    -0.86
    <pad>
    -0.86
    [@BOS@]
    -0.86
    POSITIVE LOGITS
    raszamy
    0.28
     sonre
    0.28
    makaian
    0.27
    （
    0.26
    -
    0.25
    AlterField
    0.25
    (
    0.25
    ,
    0.25
    *
    0.24
     (
    0.24
    Act Density 0.676%

    No Known Activations