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

    Neuronpedia

    INDEX
    Explanations

    "I'm" and "but"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shoe
    -0.07
    (pwd
    -0.07
     mongodb
    -0.06
     nguyện
    -0.06
     cooldown
    -0.06
    _details
    -0.06
     twilight
    -0.06
     باب
    -0.06
     Db
    -0.06
    _device
    -0.06
    POSITIVE LOGITS
    ();
↵
↵
↵
    0.07
    SAME
    0.06
    Pose
    0.06
     //
↵
↵
    0.06
    �
    0.06
    láv
    0.06
     ува
    0.06
     Romanian
    0.06
    ()"↵
    0.06
     %↵
    0.06
    Act Density 0.050%

    No Known Activations