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

    Neuronpedia

    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EZ
    -0.07
     trả
    -0.07
    (Arg
    -0.07
    一举
    -0.07
     cy
    -0.07
    可视
    -0.07
    Translated
    -0.07
     RU
    -0.06
     run
    -0.06
     integ
    -0.06
    POSITIVE LOGITS
    weight
    0.08
    ɰ
    0.08
     Weight
    0.08
    重
    0.08
     weight
    0.08
    作家
    0.07
     İnsan
    0.07
     weights
    0.07
    טה
    0.07
    兒子
    0.07
    Act Density 0.032%

    No Known Activations