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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     newline
    -0.07
    触发
    -0.07
    hart
    -0.07
    legal
    -0.07
    顺利
    -0.07
    azes
    -0.07
    Human
    -0.06
    𫍯
    -0.06
    惊喜
    -0.06
     moist
    -0.06
    POSITIVE LOGITS
     cm
    0.08
     Ltd
    0.07
     FONT
    0.07
     ofrece
    0.07
     Fat
    0.07
     rumored
    0.07
    关键是
    0.07
     señ
    0.06
     �
    0.06
    科技大学
    0.06
    Act Density 0.115%

    No Known Activations