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

    Neuronpedia

    INDEX
    Explanations

    delete

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    自在
    -0.07
    rated
    -0.07
    提出的
    -0.06
    🅦
    -0.06
    eeee
    -0.06
    蛙
    -0.06
     Gamma
    -0.06
    �
    -0.06
    涔
    -0.06
    ඞ
    -0.06
    POSITIVE LOGITS
     proj
    0.08
     район
    0.07
    小区
    0.07
     пыта
    0.07
    riages
    0.07
     LOC
    0.07
    演员
    0.07
     BITS
    0.07
    .Details
    0.06
     privilege
    0.06
    Act Density 0.009%

    No Known Activations