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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     userManager
    -0.08
    ÅŸ
    -0.06
    .Executor
    -0.06
     etti
    -0.06
    Network
    -0.06
    _expr
    -0.06
     hardly
    -0.06
    Bookmark
    -0.06
     Ethernet
    -0.06
     blindness
    -0.06
    POSITIVE LOGITS
    [vertex
    0.07
    Fre
    0.07
    ollapse
    0.06
    enth
    0.06
     sản
    0.06
     zarar
    0.06
     عبار
    0.06
    FILENAME
    0.06
     delightful
    0.06
    arrant
    0.06
    Act Density 0.001%

    No Known Activations