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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    по
    -0.07
    ету
    -0.07
     Zo
    -0.06
    voří
    -0.06
    quotelev
    -0.06
    最高
    -0.06
     pueda
    -0.06
    вает
    -0.06
    _By
    -0.06
    Так
    -0.06
    POSITIVE LOGITS
     an
    0.08
     a
    0.07
    (savedInstanceState
    0.07
    /logger
    0.06
    /signup
    0.06
    _classifier
    0.06
    _needed
    0.06
    ,request
    0.06
     WW
    0.06
    (for
    0.06
    Act Density 0.039%

    No Known Activations