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

    Neuronpedia

    INDEX
    Explanations

    backslash characters, indicating formatting or LaTeX commands in the text

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

    LaTeX markup

    np_acts-logits-general · gemini-2.0-flash

    academic paper identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.84
     Administrativna
    -0.82
    aarrggbb
    -0.82
     betweenstory
    -0.81
    -0.78
    iſten
    -0.78
    ſehen
    -0.77
    tagHelperRunner
    -0.77
     lenker
    -0.74
    bootstrapcdn
    -0.74
    POSITIVE LOGITS
    \
    0.75
    <h2>
    0.66
    1
    0.58
    The
    0.56
    <b>
    0.55
    ↵↵
    0.54
     
    0.48
    5
    0.47
    <h1>
    0.47
    <bos>
    0.45
    Act Density 0.032%

    No Known Activations