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

    Neuronpedia

    INDEX
    Explanations

    work

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ин
    -0.07
    <{
    -0.06
     суще
    -0.06
     cop
    -0.06
     los
    -0.06
    urus
    -0.06
    ooks
    -0.06
    inati
    -0.06
     vay
    -0.06
    кий
    -0.06
    POSITIVE LOGITS
     work
    0.07
     shel
    0.07
     mounts
    0.07
    ]))
↵
    0.07
     bicycles
    0.06
     М
    0.06
     Bütün
    0.06
    업
    0.06
     CONTRIBUT
    0.06
    squ
    0.06
    Act Density 0.027%

    No Known Activations