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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating structuring elements in the document

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

    Authentication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -1.00
    -0.88
     betweenstory
    -0.85
    setVerticalGroup
    -0.81
    ſcher
    -0.80
    IntoConstraints
    -0.79
    ſammen
    -0.78
    rungsseite
    -0.77
    tvguidetime
    -0.76
    majánló
    -0.76
    POSITIVE LOGITS
    The
    0.79
    <b>
    0.75
    {
    0.74
    <strong>
    0.71
     the
    0.69
    (
    0.62
     The
    0.60
    }{*}{
    0.59
    <h2>
    0.57
    <i>
    0.57
    Act Density 0.000%

    No Known Activations