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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zůst
    -0.06
     suspicious
    -0.06
     swap
    -0.06
     occurrences
    -0.06
     Utility
    -0.06
     forgot
    -0.06
     geographical
    -0.06
     cameras
    -0.06
     orch
    -0.06
     above
    -0.06
    POSITIVE LOGITS
    _weight
    0.08
    uario
    0.07
     jednak
    0.07
    exampleModalLabel
    0.07
    Plans
    0.07
     addCriterion
    0.07
    умент
    0.07
    っぱ
    0.06
    是什么
    0.06
    trer
    0.06
    Act Density 0.045%

    No Known Activations