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

    Neuronpedia

    INDEX
    Explanations

    Levels/Hierarchies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ele
    -0.06
    ",'
    -0.06
    }`,↵
    -0.06
     вона
    -0.06
    asting
    -0.06
    },↵↵
    -0.06
    πον
    -0.06
    develop
    -0.06
     ओर
    -0.06
     kích
    -0.06
    POSITIVE LOGITS
     historians
    0.06
    processors
    0.06
    ザイン
    0.06
    	es
    0.06
    实施
    0.06
    لس
    0.06
    PACKAGE
    0.06
    _subject
    0.06
    (Array
    0.06
    IALOG
    0.06
    Act Density 0.042%

    No Known Activations