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

    Neuronpedia

    INDEX
    Explanations

    perfect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     taps
    -0.07
    _NOTIFY
    -0.06
     preferring
    -0.06
    _ptrs
    -0.06
    gem
    -0.06
     introduces
    -0.06
     DLC
    -0.06
     soon
    -0.06
    剛
    -0.06
    Deletes
    -0.06
    POSITIVE LOGITS
    ;")↵
    0.07
     Ellie
    0.06
     konut
    0.06
     lep
    0.06
     Dex
    0.06
    /ubuntu
    0.06
     Delhi
    0.06
    ..
    0.06
    .Amount
    0.06
     Львів
    0.06
    Act Density 0.018%

    No Known Activations