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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Show
    -0.07
    -going
    -0.07
    نامه
    -0.07
     mojo
    -0.06
    truck
    -0.06
     수강
    -0.06
    mě
    -0.06
    |#
    -0.05
    avana
    -0.05
    aney
    -0.05
    POSITIVE LOGITS
    .cornerRadius
    0.07
     }(
    0.07
     propose
    0.07
     glob
    0.07
     разработ
    0.07
    510
    0.06
     --------
    0.06
    ikipedia
    0.06
    (Constructor
    0.06
     understands
    0.06
    Act Density 0.003%

    No Known Activations