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

    Neuronpedia

    INDEX
    Explanations

    ulin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ce
    -0.07
     bore
    -0.07
    =e
    -0.07
     semaphore
    -0.07
     lets
    -0.06
    Luke
    -0.06
     dece
    -0.06
    *>(&
    -0.06
     để
    -0.06
     oro
    -0.06
    POSITIVE LOGITS
    in
    0.15
    IN
    0.15
    un
    0.10
    bin
    0.10
    ин
    0.10
    yn
    0.10
    atin
    0.10
    kin
    0.10
    abin
    0.09
     Tin
    0.09
    Act Density 0.235%

    No Known Activations