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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ampa
    -0.06
    ertain
    -0.06
     وهي
    -0.06
    ニー
    -0.06
     нами
    -0.06
    teri
    -0.06
    �
    -0.06
     specific
    -0.06
     affid
    -0.06
     Svens
    -0.06
    POSITIVE LOGITS
    */
    0.07
     simulator
    0.07
    -down
    0.06
    ，在
    0.06
    Pixel
    0.06
    ..
    0.06
    (priv
    0.06
     Classified
    0.06
     College
    0.06
    (db
    0.06
    Act Density 0.001%

    No Known Activations