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

    Neuronpedia

    INDEX
    Explanations

    frequent references to specific articles or nouns

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

    Preceding certain punctuation or special characters

    np_acts-logits-general · gemini-2.0-flash

    German words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onboarding
    -0.71
     perfekte
    -0.70
     impactful
    -0.69
     playbook
    -0.68
     curated
    -0.65
     ecosistema
    -0.65
     demographics
    -0.64
     vibe
    -0.63
    そこまで
    -0.62
     laborales
    -0.62
    POSITIVE LOGITS
     muß
    0.74
    faßt
    0.66
     daß
    0.64
     Schluß
    0.62
    luß
    0.61
     Meksiku
    0.61
     betreffenden
    0.60
     present
    0.57
     mußte
    0.57
     débris
    0.56
    Act Density 0.670%

    No Known Activations