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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arac
    -0.07
     kaç
    -0.07
    "He
    -0.07
    укт
    -0.06
     сделать
    -0.06
     ")
    -0.06
     irgend
    -0.06
     singly
    -0.06
    하지
    -0.06
     آل
    -0.06
    POSITIVE LOGITS
     Down
    0.07
    AIM
    0.07
     Sniper
    0.07
     DOWN
    0.07
    _sep
    0.07
    	MPI
    0.07
     Sinclair
    0.07
     snapshot
    0.06
     opcode
    0.06
     Prom
    0.06
    Act Density 0.037%

    No Known Activations