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

    Neuronpedia

    INDEX
    Explanations

    statistical significance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     없
    -0.07
    気が
    -0.07
     좋아
    -0.07
     güney
    -0.06
    었
    -0.06
    �
    -0.06
     lối
    -0.06
    case
    -0.06
    alace
    -0.06
    Autowired
    -0.06
    POSITIVE LOGITS
     knights
    0.08
     cos
    0.07
     Governments
    0.07
     window
    0.07
     GOOGLE
    0.07
    Mirror
    0.07
     deputy
    0.06
    .category
    0.06
     calendar
    0.06
     Tensor
    0.06
    Act Density 0.017%

    No Known Activations