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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .MoveNext
    -0.07
    .Container
    -0.07
    _OVERFLOW
    -0.06
    Fran
    -0.06
    Unauthorized
    -0.06
     ApplicationContext
    -0.06
     CALLBACK
    -0.06
    _elapsed
    -0.06
     Elaine
    -0.06
    .Attributes
    -0.06
    POSITIVE LOGITS
    -short
    0.08
    n
    0.07
    !!!↵
    0.07
     jump
    0.06
    :')↵
    0.06
     feeder
    0.06
     ）↵
    0.06
    ，↵
    0.06
     chẳng
    0.06
     quickly
    0.06
    Act Density 0.000%

    No Known Activations