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

    Neuronpedia

    INDEX
    Explanations

    instances of powerful numeric values

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

    constants and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    astéroïdes
    -0.42
    Хьажоргаш
    -0.40
    PropertyChanging
    -0.39
     torno
    -0.37
     bientôt
    -0.34
    ientôt
    -0.33
    PRD
    -0.33
    ViewFeatures
    -0.32
     ddelweddau
    -0.32
    PageModule
    -0.32
    POSITIVE LOGITS
    RenderAtEndOf
    0.63
    ✨:
    0.59
    +#+
    0.59
    0.59
    __(/*!
    0.54
    
    0.52
    :+:
    0.51
    0.50
    Portail
    0.50
     Geſch
    0.50
    Act Density 0.005%

    No Known Activations