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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ierarchical
    -0.06
    Wire
    -0.06
     ux
    -0.06
     phased
    -0.06
    Brown
    -0.06
    lever
    -0.06
     Hist
    -0.06
    .W
    -0.06
    ]){
↵
    -0.06
    //*
    -0.06
    POSITIVE LOGITS
    compress
    0.07
    155
    0.06
    CRYPT
    0.06
     mpfr
    0.06
     absorbing
    0.06
     ΕΛ
    0.06
     قسمت
    0.06
    준
    0.06
    IDEOS
    0.06
     JAXB
    0.06
    Act Density 0.009%

    No Known Activations