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

    Neuronpedia

    INDEX
    Explanations

    Teacups and teapots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Corridor
    -0.08
    _Ver
    -0.08
    策
    -0.08
    交通
    -0.08
    Consent
    -0.07
    _checkpoint
    -0.07
     opportun
    -0.07
    制度
    -0.07
     corridors
    -0.07
    -Bahn
    -0.07
    POSITIVE LOGITS
     pottery
    0.12
     dishwasher
    0.10
     utens
    0.10
     mugs
    0.10
     пить
    0.10
     cozinha
    0.10
     Ugly
    0.10
     Dishwasher
    0.10
     ceramic
    0.10
     beverage
    0.10
    Act Density 0.046%

    No Known Activations