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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seni
    -0.07
     increases
    -0.07
     yield
    -0.07
    顶
    -0.07
     protecting
    -0.06
    ./
    -0.06
    equalTo
    -0.06
    VILLE
    -0.06
     yields
    -0.06
    _MONITOR
    -0.06
    POSITIVE LOGITS
     Harley
    0.07
     Rhe
    0.06
    icmp
    0.06
     František
    0.06
     setData
    0.06
    〈
    0.06
     TE
    0.06
     squarely
    0.06
     SY
    0.06
                              ↵
    0.06
    Act Density 0.000%

    No Known Activations