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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics related to demographics or economic information

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

    percentages and millions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.47
    ;
    -0.36
     Schwerpunkt
    -0.35
    by
    -0.34
    ↵↵
    -0.34
    impresa
    -0.33
    a
    -0.32
    ).
    -0.31
    .;
    -0.30
    。
    -0.30
    POSITIVE LOGITS
    AndEndTag
    1.08
     CreateTagHelper
    1.00
    RegressionTest
    0.94
    AddTagHelper
    0.93
    <unused8>
    0.90
    [@BOS@]
    0.90
    <unused28>
    0.90
    <unused79>
    0.90
    <unused68>
    0.90
    <pad>
    0.89
    Act Density 0.160%

    No Known Activations