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

    Neuronpedia

    INDEX
    Explanations

    formatting symbols and markup language syntax

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

    LaTeX formatting

    np_acts-logits-general · gemini-2.0-flash

    latex labels and ends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -1.07
     للمعارف
    -0.90
    aarrggbb
    -0.88
     kaarangay
    -0.87
     AssemblyVersion
    -0.84
     otomatig
    -0.82
    Personendaten
    -0.79
    tvguidetime
    -0.77
     lenker
    -0.77
     protoimpl
    -0.77
    POSITIVE LOGITS
    <h2>
    0.74
    \
    0.71
    <b>
    0.64
    The
    0.58
    <h4>
    0.57
    <h3>
    0.53
    <strong>
    0.53
    I
    0.52
    We
    0.51
    ↵↵
    0.50
    Act Density 0.042%

    No Known Activations