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

    Neuronpedia

    INDEX
    Explanations

    ule

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aluminum
    -0.08
    失误
    -0.07
    しっ
    -0.07
    lässig
    -0.07
    黝
    -0.07
     silky
    -0.06
    _absolute
    -0.06
     b
    -0.06
     absorbing
    -0.06
    ⦿
    -0.06
    POSITIVE LOGITS
    prints
    0.07
    ule
    0.07
    ucha
    0.06
     community
    0.06
     Andrew
    0.06
     {
↵
↵
↵
    0.06
    uga
    0.06
     Dallas
    0.06
     TODO
    0.06
     Comcast
    0.06
    Act Density 0.001%

    No Known Activations