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

    Neuronpedia

    INDEX
    Explanations

    shield

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     internet
    -0.07
    Output
    -0.07
    нимать
    -0.07
     disasters
    -0.07
    /article
    -0.06
     Ed
    -0.06
     evil
    -0.06
    incinnati
    -0.06
     properly
    -0.06
     Wilkinson
    -0.06
    POSITIVE LOGITS
     باق
    0.07
    getDoctrine
    0.07
    ASA
    0.06
     кім
    0.06
     jej
    0.06
    riel
    0.06
    ترل
    0.06
     ovarian
    0.06
     pulver
    0.06
    レイ
    0.06
    Act Density 0.000%

    No Known Activations