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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fotograf
    -0.07
     区
    -0.07
     inversion
    -0.07
     वस
    -0.06
     decimals
    -0.06
     눈을
    -0.06
    Conversion
    -0.06
     IndexError
    -0.06
    thinking
    -0.06
     usability
    -0.06
    POSITIVE LOGITS
    ляет
    0.07
     Two
    0.07
    }->{
    0.07
     [-
    0.07
    +++
    0.07
     ‏
    0.07
    ,…
    0.06
    _SS
    0.06
     tokenId
    0.06
     bitter
    0.06
    Act Density 0.008%

    No Known Activations