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

    Neuronpedia

    INDEX
    Explanations

    Unexpected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cors
    -0.06
    723
    -0.06
    _FUNCTION
    -0.06
     Бол
    -0.06
     destructive
    -0.06
    __.
    -0.06
    661
    -0.06
     destruction
    -0.06
    編
    -0.06
    Owner
    -0.06
    POSITIVE LOGITS
    Unexpected
    0.09
     Unexpected
    0.08
    unexpected
    0.08
    _ra
    0.07
    обра�
    0.07
    esis
    0.07
     Detected
    0.06
     wij
    0.06
     чуть
    0.06
    elong
    0.06
    Act Density 0.001%

    No Known Activations