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

    Neuronpedia

    INDEX
    Explanations

    PATCH

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whites
    -0.07
    现代
    -0.07
     Electronic
    -0.07
    trasound
    -0.07
    	CC
    -0.07
    sgi
    -0.07
    阿拉伯
    -0.07
    setValue
    -0.07
    ünc
    -0.07
    深处
    -0.07
    POSITIVE LOGITS
    켤
    0.07
     portfolio
    0.07
    /block
    0.06
    忌
    0.06
     đúng
    0.06
    .spi
    0.06
     Mur
    0.06
    ┬
    0.06
     начал
    0.06
    Starting
    0.06
    Act Density 0.001%

    No Known Activations