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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    복지
    -0.07
     Cout
    -0.07
    -mod
    -0.07
     FAT
    -0.07
     Drinking
    -0.06
     mas
    -0.06
    _ud
    -0.06
    mill
    -0.06
     compete
    -0.06
     Auction
    -0.06
    POSITIVE LOGITS
     trục
    0.07
    อป
    0.07
     Sah
    0.06
     เขต
    0.06
    ента
    0.06
     […]...↵
    0.06
     elasticity
    0.06
    _FORCE
    0.06
     scarf
    0.06
    "},{"
    0.06
    Act Density 0.000%

    No Known Activations