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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "goodness."

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

    the quality of goodness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mobileqq
    -0.59
    存于互联网档案馆
    -0.55
    Infl
    -0.49
    店
    -0.47
    Mobile
    -0.44
    zepam
    -0.42
     pylint
    -0.41
    Drag
    -0.41
    Avi
    -0.41
     mobi
    -0.41
    POSITIVE LOGITS
     goodness
    2.16
     Goodness
    2.03
    Goodness
    1.86
     bonté
    1.13
     kebaikan
    0.89
    ness
    0.68
     gosh
    0.63
    NESS
    0.63
     bienfaits
    0.63
     Goodman
    0.60
    Act Density 0.004%

    No Known Activations