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

    Neuronpedia

    INDEX
    Explanations

    frequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Island
    -0.07
     чес
    -0.07
    水
    -0.06
     thee
    -0.06
     Owners
    -0.06
     queues
    -0.06
     cholesterol
    -0.06
     бизнес
    -0.06
     allowing
    -0.06
     Deep
    -0.06
    POSITIVE LOGITS
    ━�
    0.07
    ThanOrEqualTo
    0.06
     والتي
    0.06
    uD
    0.06
    šit
    0.06
     urlpatterns
    0.06
    .pref
    0.06
    렇
    0.06
    tep
    0.06
    О
    0.06
    Act Density 0.014%

    No Known Activations