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

    Neuronpedia

    INDEX
    Explanations

    court cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alm
    -0.07
     envelopes
    -0.07
    Precision
    -0.07
     pantry
    -0.07
    overall
    -0.07
    经历过
    -0.07
    ane
    -0.07
    一封
    -0.07
    连线
    -0.06
    鞡
    -0.06
    POSITIVE LOGITS
    另一种
    0.08
     어떤
    0.08
     będ
    0.07
     qed
    0.07
    のが
    0.07
    するのが
    0.07
     UIKit
    0.07
    天国继续
    0.07
    不少
    0.07
    :)])
    0.06
    Act Density 0.022%

    No Known Activations