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

    Neuronpedia

    INDEX
    Explanations

    InstanceState

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mez
    -0.06
     unix
    -0.06
     бол
    -0.06
     viel
    -0.06
     bfs
    -0.06
     crab
    -0.06
     mö
    -0.06
     ngừng
    -0.06
     Chall
    -0.06
     시험
    -0.06
    POSITIVE LOGITS
     Pavilion
    0.07
    orget
    0.07
    ossip
    0.06
     Vol
    0.06
     consume
    0.06
     researching
    0.06
    _slave
    0.06
     getInstance
    0.06
    lush
    0.06
    localObject
    0.06
    Act Density 0.002%

    No Known Activations