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

    Neuronpedia

    INDEX
    Explanations

    variations and distinctions among categories or types

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

    "different" followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    different types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    charCode
    -0.59
     âmes
    -0.47
     pères
    -0.46
    IconModule
    -0.45
    scrollView
    -0.44
     îns
    -0.44
    trzyma
    -0.44
    kemeja
    -0.43
     devenus
    -0.43
    étaires
    -0.42
    POSITIVE LOGITS
    Different
    1.02
     Different
    1.00
     different
    0.99
     DIFFERENT
    0.98
    different
    0.98
     farklı
    0.80
    erent
    0.76
     diferente
    0.71
     différent
    0.69
     distinta
    0.68
    Act Density 0.151%

    No Known Activations