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

    Neuronpedia

    INDEX
    Explanations

    li

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ::*
    -0.08
    やって
    -0.07
     completion
    -0.07
     collected
    -0.06
     jejich
    -0.06
    /tree
    -0.06
     shelves
    -0.06
     içindeki
    -0.06
    _buttons
    -0.06
    емого
    -0.06
    POSITIVE LOGITS
    urers
    0.07
     Leg
    0.07
    라인
    0.07
    Preference
    0.07
     gün
    0.07
     disruption
    0.06
    冊
    0.06
    angu
    0.06
    (ValueError
    0.06
    廊
    0.06
    Act Density 0.008%

    No Known Activations