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

    Neuronpedia

    INDEX
    Explanations

    various types of mathematical and structural formatting symbols and indicators

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

    LaTeX math mode delimiters

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation or delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused74>
    -0.97
    <unused8>
    -0.97
    <unused52>
    -0.97
    <unused41>
    -0.97
    <unused68>
    -0.97
    <unused79>
    -0.97
    <unused16>
    -0.97
    <unused14>
    -0.96
    <unused3>
    -0.96
    [@BOS@]
    -0.96
    POSITIVE LOGITS
    |}{
    0.74
    }{*}{
    0.70
    <b>
    0.70
    <strong>
    0.66
     "
    0.60
    ("
    0.60
    ('
    0.59
    <td>
    0.56
     (
    0.55
    <i>
    0.54
    Act Density 0.252%

    No Known Activations