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

    Neuronpedia

    INDEX
    Explanations

    Software licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    꺠
    -0.08
     problems
    -0.07
    龙头
    -0.07
    獲得
    -0.07
    人口
    -0.07
     step
    -0.07
    liter
    -0.06
    带头
    -0.06
    韧性
    -0.06
     mane
    -0.06
    POSITIVE LOGITS
     antibodies
    0.08
    售卖
    0.08
     overriding
    0.08
    usaha
    0.08
     Âu
    0.08
     Packers
    0.08
     OnCollision
    0.07
     Reject
    0.07
    ridged
    0.07
     sheds
    0.07
    Act Density 0.032%

    No Known Activations