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

    Neuronpedia

    INDEX
    Explanations

    text in specific formats, like multiple choice questions, lists, underlined blanks, or censored words

    oai_token-act-pair · gemini-2.0-flash

    Incomplete/truncated texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    saraba
    -0.58
    lateur
    -0.53
     saw
    -0.50
    Referències
    -0.50
    saw
    -0.48
    ChildScrollView
    -0.46
    ospels
    -0.46
    ука
    -0.45
     Saw
    -0.43
    欄
    -0.43
    POSITIVE LOGITS
    contentLoaded
    0.76
    awtextra
    0.72
     مرئيه
    0.64
     متعلقه
    0.61
    thâu
    0.61
     BoxFit
    0.61
    featureID
    0.60
    setVerticalGroup
    0.60
    RegressionTest
    0.60
    tagHelperRunner
    0.59
    Act Density 0.864%

    No Known Activations