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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics related to health measurements or study results

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

    frequency, units, and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    We
    -0.27
    I
    -0.27
    
    -0.25
    Also
    -0.23
    ↵↵
    -0.22
    ↵
    -0.22
    And
    -0.21
    The
    -0.20
    providedIn
    -0.20
    </blockquote>
    -0.20
    POSITIVE LOGITS
    enablog
    0.91
     fashiola
    0.91
    <unused68>
    0.90
    <unused51>
    0.90
    <unused79>
    0.90
    <unused74>
    0.90
    [@BOS@]
    0.90
    <unused16>
    0.90
    <unused14>
    0.90
    <unused8>
    0.90
    Act Density 0.208%

    No Known Activations