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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Grove
    -0.07
    _boolean
    -0.07
    Lets
    -0.07
    ="//
    -0.07
    ीस
    -0.06
     to
    -0.06
    Shows
    -0.06
     Void
    -0.06
    ujemy
    -0.06
    	A
    -0.06
    POSITIVE LOGITS
    :first
    0.07
     fucked
    0.06
    oauth
    0.06
    uncated
    0.06
     boarding
    0.06
    اسر
    0.06
    �
    0.06
     команд
    0.06
    (server
    0.06
    ersist
    0.06
    Act Density 0.070%

    No Known Activations