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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements and statistics related to various subjects

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

    Units of measure

    np_acts-logits-general · gemini-2.0-flash

    units of measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.82
    Datuak
    -0.81
     Roskov
    -0.72
    :✨
    -0.72
    sizeCache
    -0.70
     utafitiHapana
    -0.67
     виправивши
    -0.66
    SharedCtor
    -0.63
    WriteTagHelper
    -0.62
     تضيفلها
    -0.61
    POSITIVE LOGITS
     for
    0.49
     the
    0.47
    째
    0.45
    ULS
    0.44
     this
    0.44
    .
    0.43
     in
    0.43
     
    0.43
     of
    0.41
    rs
    0.39
    Act Density 0.464%

    No Known Activations