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

    Neuronpedia

    INDEX
    Explanations

    navigation menus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .master
    -0.07
     invaders
    -0.07
    κας
    -0.07
     WORLD
    -0.07
    nip
    -0.06
     Assert
    -0.06
    كر
    -0.06
     déf
    -0.06
     PASS
    -0.06
    story
    -0.06
    POSITIVE LOGITS
    Invocation
    0.07
     advisable
    0.07
     Ελλάδα
    0.06
     Illegal
    0.06
     routines
    0.06
    という
    0.06
    Slot
    0.06
    Honestly
    0.06
     yüzden
    0.06
    median
    0.06
    Act Density 0.001%

    No Known Activations