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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ptrs
    -0.07
    _markers
    -0.06
    _pipe
    -0.06
    ωνα
    -0.06
     ambigu
    -0.06
    _S
    -0.06
     often
    -0.06
    fixtures
    -0.06
     invaders
    -0.06
     mover
    -0.06
    POSITIVE LOGITS
    мм
    0.07
    ,string
    0.06
     대구
    0.06
     GRID
    0.06
    ({_
    0.06
    LOY
    0.06
    öz
    0.06
    [column
    0.06
     ROOM
    0.06
    보다
    0.06
    Act Density 0.002%

    No Known Activations