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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated units

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

    times, speeds, or amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.71
     queſta
    -0.69
    nodoc
    -0.64
     CreateTagHelper
    -0.63
    ftagPool
    -0.63
    invokeLater
    -0.61
    Билгалдахарш
    -0.60
    setVerticalGroup
    -0.60
     nakalista
    -0.60
    ࿊
    -0.59
    POSITIVE LOGITS
     Савез
    0.32
     depending
    0.28
    featureID
    0.27
    Pautan
    0.27
     Parthen
    0.26
    InBytes
    0.25
     ennen
    0.25
    ന്
    0.25
    数年
    0.25
    assertFalse
    0.24
    Act Density 0.046%

    No Known Activations