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

    Neuronpedia

    INDEX
    Explanations

    product descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anarchy
    0.50
     blaming
    0.49
     sabotage
    0.45
     blame
    0.45
     diplomacy
    0.44
     brib
    0.44
     embezzlement
    0.44
    ifferentiate
    0.44
     Patreon
    0.43
    wikipedia
    0.43
    POSITIVE LOGITS
     vêtements
    0.62
     cookware
    0.60
     제품
    0.55
     hairst
    0.54
     producten
    0.54
    食品
    0.54
     garment
    0.54
     roofing
    0.54
     ürün
    0.53
     cosmet
    0.53
    Act Density 0.108%

    No Known Activations