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

    Neuronpedia

    INDEX
    Explanations

    complex relationships and dependencies in data

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

    decision, consequences, solution, known

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.45
    rigkeit
    -0.44
     ivelany
    -0.41
     ویکی‌پدی
    -0.40
    Autoritní
    -0.40
     Paglinawan
    -0.38
    ValueStyle
    -0.38
     linkovi
    -0.36
    brunn
    -0.36
     OkHttpClient
    -0.35
    POSITIVE LOGITS
    хьтан
    0.48
    OrNil
    0.47
     itinéraires
    0.47
    MethodManager
    0.46
    ArgsConstructor
    0.45
     дописавши
    0.43
    httphttps
    0.40
     Privacidade
    0.40
    InitVars
    0.40
    рс
    0.38
    Act Density 0.045%

    No Known Activations