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

    Neuronpedia

    INDEX
    Explanations

    Python code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     successful
    -0.07
     čím
    -0.06
    ững
    -0.06
     어떤
    -0.06
    оба
    -0.06
    nesday
    -0.06
    _PHY
    -0.06
    _goto
    -0.06
    iệu
    -0.06
    аша
    -0.06
    POSITIVE LOGITS
     earthquake
    0.06
    .func
    0.06
     schemes
    0.06
     blessings
    0.06
     Configure
    0.06
     새
    0.06
     demean
    0.06
     quaint
    0.06
     collided
    0.06
    ---↵
    0.06
    Act Density 0.002%

    No Known Activations