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

    Neuronpedia

    INDEX
    Explanations

    distinguish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     =&
    -0.08
     Carbon
    -0.07
     возможно
    -0.07
     Cape
    -0.07
    Iran
    -0.07
    rf
    -0.07
     Omar
    -0.07
     Automotive
    -0.07
     erfolgre
    -0.07
     Thief
    -0.07
    POSITIVE LOGITS
    istinguish
    0.08
     distinguish
    0.07
     distinct
    0.07
     discern
    0.07
     distinction
    0.07
     distinguished
    0.07
    _DISPATCH
    0.06
    уск
    0.06
     distinguishing
    0.06
    join
    0.06
    Act Density 0.027%

    No Known Activations