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

    Neuronpedia

    INDEX
    Explanations

    nouns related to documentation and procedures

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

    after questions or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    hearing aid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    — 
    -0.83
     NSCoder
    -0.77
     Audiodateien
    -0.75
     سكانية
    -0.73
    DockStyle
    -0.70
    rawDesc
    -0.70
    resaid
    -0.69
    moiselle
    -0.67
     שוליים
    -0.67
    ressee
    -0.66
    POSITIVE LOGITS
     of
    0.61
     is
    0.57
     was
    0.55
     for
    0.51
     unit
    0.48
     will
    0.48
     can
    0.47
     program
    0.46
     must
    0.46
    型
    0.46
    Act Density 1.130%

    No Known Activations