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

    Neuronpedia

    INDEX
    Explanations

    special characters or formatting issues

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

    special characters or accents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endregion
    -0.52
    __":
    -0.50
    <h1>
    -0.50
    ink
    -0.50
    ing
    -0.49
    oid
    -0.48
    __':
    -0.48
    </tr>
    -0.47
    omit
    -0.46
    )}{
    -0.46
    POSITIVE LOGITS
     â
    1.62
    â
    1.18
     Â
    0.95
    lâ
    0.88
     sâ
    0.81
     Mâ
    0.79
    câ
    0.78
    Â
    0.75
     lâ
    0.72
     Bâ
    0.72
    Act Density 0.009%

    No Known Activations