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

    Neuronpedia

    INDEX
    Explanations

    transform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frances
    -0.07
    prowadzić
    -0.07
     المس
    -0.07
    拨
    -0.07
     Coron
    -0.07
    练习
    -0.07
     кноп
    -0.07
     podcasts
    -0.07
     SOCKET
    -0.07
     noises
    -0.07
    POSITIVE LOGITS
     transform
    0.09
     transformed
    0.08
    랩
    0.07
    ALTER
    0.07
    	transform
    0.07
    對方
    0.07
    ظاهرة
    0.07
     transformation
    0.07
    ولد
    0.07
    ABI
    0.06
    Act Density 0.027%

    No Known Activations