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

    Neuronpedia

    INDEX
    Explanations

    possible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ------+
    -0.07
    립
    -0.07
    ี,
    -0.06
    واهد
    -0.06
    IO
    -0.06
    ριά
    -0.06
     disease
    -0.06
    resp
    -0.06
     authentication
    -0.06
    圭
    -0.06
    POSITIVE LOGITS
    .createObject
    0.07
     Kraft
    0.07
     dro
    0.06
     ADMIN
    0.06
     постоянно
    0.06
     Lect
    0.06
    	Created
    0.06
    اقتص
    0.06
    (H
    0.06
     uniformly
    0.06
    Act Density 0.023%

    No Known Activations