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

    Neuronpedia

    INDEX
    Explanations

    Improvements and differences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itch
    -0.07
     Edition
    -0.06
     altern
    -0.06
     Grant
    -0.06
    BLACK
    -0.06
     ****************************************************************
    -0.06
     WaitForSeconds
    -0.06
    Lesson
    -0.06
    Hugh
    -0.06
    Quiet
    -0.06
    POSITIVE LOGITS
    ैश
    0.07
     deploying
    0.07
     planner
    0.06
    asyonu
    0.06
    _REPO
    0.06
     wing
    0.06
     destek
    0.06
    Operators
    0.06
     hedef
    0.06
     functor
    0.06
    Act Density 0.476%

    No Known Activations