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

    Neuronpedia

    INDEX
    Explanations

    formatting elements typically used in mathematical documents or equations

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

    LaTeX aligned environments

    np_acts-logits-general · gemini-2.0-flash

    aligned equations and cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.72
    -0.66
     spacy
    -0.61
     queſta
    -0.61
     vPvB
    -0.61
     MainAxisSize
    -0.60
     ſind
    -0.60
    iſen
    -0.60
    stdc
    -0.60
    Chham
    -0.60
    POSITIVE LOGITS
    hline
    2.25
    hdashline
    0.62
    <tr>
    0.62
    cline
    0.60
    Override
    0.55
    hi
    0.51
    tabular
    0.50
    here
    0.49
    1
    0.47
    na
    0.46
    Act Density 0.037%

    No Known Activations