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

    Neuronpedia

    INDEX
    Explanations

    cell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    36
    -0.06
    LOOD
    -0.06
    175
    -0.06
     уровня
    -0.06
    CT
    -0.06
     MST
    -0.06
    -Agent
    -0.06
     Shirt
    -0.06
    417
    -0.06
     lost
    -0.06
    POSITIVE LOGITS
    Uses
    0.06
     accompanying
    0.06
     Indones
    0.06
    Compar
    0.06
     satin
    0.06
     simplify
    0.06
     кож
    0.06
     creo
    0.06
    要求
    0.06
     Guid
    0.06
    Act Density 0.018%

    No Known Activations