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

    Neuronpedia

    INDEX
    Explanations

    instances of variables represented in mathematical notation

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

    LaTeX \mathbf command

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.57
    ItemLayout
    -0.54
    躇
    -0.52
     includes
    -0.51
    */,
    -0.49
    ruptedException
    -0.49
    tagHelperRunner
    -0.48
     improv
    -0.47
     Include
    -0.47
    include
    -0.47
    POSITIVE LOGITS
    mathbf
    1.65
    er
    0.77
     vectorielles
    0.69
    <strong>
    0.65
    <b>
    0.65
    textbf
    0.59
     vectorielle
    0.59
    mathbb
    0.56
     băr
    0.53
    mathcal
    0.52
    Act Density 0.023%

    No Known Activations