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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Checks
    -0.08
     gọi
    -0.07
    .Lo
    -0.07
     Grad
    -0.07
    ipp
    -0.07
    ={$
    -0.07
     مكان
    -0.06
     parçası
    -0.06
     CEOs
    -0.06
     Presentation
    -0.06
    POSITIVE LOGITS
     effic
    0.06
     illum
    0.06
     alle
    0.06
    Parm
    0.06
     ejac
    0.06
    URIComponent
    0.06
    range
    0.06
    ()));↵
    0.06
    TCP
    0.06
     lexical
    0.06
    Act Density 0.001%

    No Known Activations