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

    Neuronpedia

    INDEX
    Explanations

    UN resolutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HEAD
    -0.06
    _xyz
    -0.06
    rientation
    -0.06
    rowsable
    -0.06
     WWW
    -0.06
     ilgi
    -0.06
    yg
    -0.06
    ilit
    -0.06
    Sin
    -0.06
     Fukushima
    -0.06
    POSITIVE LOGITS
     xsi
    0.07
    (segment
    0.07
    :{
    0.07
    ]){
↵
    0.07
    +#
    0.06
    langle
    0.06
     aime
    0.06
    HttpException
    0.06
     Rodriguez
    0.06
     Ning
    0.06
    Act Density 0.021%

    No Known Activations