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

    Neuronpedia

    INDEX
    Explanations

    IL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Pin
    -0.07
     sharp
    -0.06
     Tooth
    -0.06
    く
    -0.06
    pute
    -0.06
    xdd
    -0.06
     は
    -0.06
     Boat
    -0.06
    _extended
    -0.06
     brisk
    -0.06
    POSITIVE LOGITS
    [S
    0.08
    erts
    0.08
     irc
    0.07
    -progress
    0.06
    ceive
    0.06
    ượng
    0.06
     상
    0.06
    COM
    0.06
     lyric
    0.06
    'S
    0.06
    Act Density 0.024%

    No Known Activations