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

    Neuronpedia

    INDEX
    Explanations

    HTML elements and attributes used in web page structure

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

    html attribute assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.37
    but
    -0.31
    )
    -0.29
    ;
    -0.28
    impl
    -0.28
    to
    -0.28
    '
    -0.28
    3
    -0.28
    of
    -0.27
    1
    -0.27
    POSITIVE LOGITS
    MigrationBuilder
    1.01
    IsMutable
    1.01
    <unused23>
    0.91
    <unused51>
    0.91
    <unused14>
    0.91
    [@BOS@]
    0.91
    <unused28>
    0.91
    <unused41>
    0.91
    <unused17>
    0.91
    <pad>
    0.91
    Act Density 0.011%

    No Known Activations