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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diamond
    -0.07
     Pruitt
    -0.07
     dia
    -0.07
     I
    -0.07
     Umb
    -0.06
    _horizontal
    -0.06
     Τζ
    -0.06
     Arn
    -0.06
     مورد
    -0.06
    you
    -0.06
    POSITIVE LOGITS
    —as
    0.07
    —which
    0.07
     methodology
    0.07
    .restart
    0.07
    (pages
    0.07
    which
    0.06
    ">
↵
    0.06
    directory
    0.06
     which
    0.06
    '>
↵
    0.06
    Act Density 0.105%

    No Known Activations