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

    Neuronpedia

    INDEX
    Explanations

    gambling probabilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    純
    -0.07
    ком
    -0.07
    amines
    -0.06
    esthesia
    -0.06
     grants
    -0.06
     nose
    -0.06
    _validation
    -0.06
     piping
    -0.06
     Philosoph
    -0.06
    دم
    -0.06
    POSITIVE LOGITS
     producción
    0.07
    -format
    0.06
    вропей
    0.06
    рю
    0.06
     تصویر
    0.06
    rish
    0.06
     суд
    0.06
    GRESS
    0.06
     说
    0.06
    ，看
    0.06
    Act Density 0.007%

    No Known Activations