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

    Neuronpedia

    INDEX
    Explanations

    evaluative language indicating judgment or opinion

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

    explaining a reason or justification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.77
    SourceChecksum
    -0.71
    脚注の使い方
    -0.70
     utafitiHapana
    -0.66
    ----</
    -0.65
    expandindo
    -0.63
    titleMargin
    -0.61
    CppMethod
    -0.60
    出版年
    -0.60
     resourceCulture
    -0.59
    POSITIVE LOGITS
    /**
    0.30
     cm
    0.29
     avvic
    0.29
    "/",
    0.28
     ад
    0.27
     nødven
    0.27
     кстати
    0.27
     Ad
    0.27
     Mol
    0.26
     Fine
    0.26
    Act Density 0.189%

    No Known Activations