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

    Neuronpedia

    INDEX
    Explanations

    64

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apters
    -0.07
    /add
    -0.07
     Items
    -0.07
     Breakfast
    -0.07
     Laurel
    -0.06
    _album
    -0.06
    _details
    -0.06
     weapon
    -0.06
     kale
    -0.06
     bob
    -0.06
    POSITIVE LOGITS
    ，在
    0.06
     gcc
    0.06
    #:
    0.06
    _INST
    0.06
     mong
    0.06
    oblin
    0.06
     déc
    0.06
    GORITH
    0.06
     موفق
    0.06
     wore
    0.06
    Act Density 0.001%

    No Known Activations