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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and dialogue indicators in text

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

    Text after quotations

    np_acts-logits-general · gemini-2.0-flash

    quoted speech and dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __(/*!
    -0.79
     AssemblyCulture
    -0.68
    InputBorder
    -0.60
    PARATUS
    -0.58
     δὲ
    -0.57
    υναι
    -0.55
    Kesimpulan
    -0.55
     Normdatei
    -0.55
     Oso
    -0.54
    DTD
    -0.54
    POSITIVE LOGITS
     The
    0.58
    awtextra
    0.53
    The
    0.50
    ExtendWith
    0.49
    DebuggerStep
    0.49
    Ignoring
    0.47
    ymce
    0.46
     LCCN
    0.46
     For
    0.45
    <eos>
    0.43
    Act Density 0.037%

    No Known Activations