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

    Neuronpedia

    INDEX
    Explanations

    numeric representations of data

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

    Numbers with decimals

    np_acts-logits-general · gemini-2.0-flash

    numbers, decimals, dosages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.64
     חיצוניים
    -0.60
    الدراسه
    -0.60
     six
    -0.59
     eighteen
    -0.57
     sechs
    -0.53
     sixteen
    -0.52
    ียบ
    -0.52
    cshtml
    -0.51
     neuf
    -0.50
    POSITIVE LOGITS
    Jîn
    0.56
    فایل‌لار
    0.55
    LEncoder
    0.54
    нік
    0.54
    InitVars
    0.53
    SourceChecksum
    0.51
     ۲۵
    0.50
    hoeddwyd
    0.49
    ########.
    0.49
    ViewFeatures
    0.49
    Act Density 0.339%

    No Known Activations