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

    Neuronpedia

    INDEX
    Explanations

    mat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fly
    -0.07
    �
    -0.07
    :border
    -0.07
    ())));↵
    -0.07
    (web
    -0.06
    ____
    -0.06
     бак
    -0.06
    يلاد
    -0.06
    .creator
    -0.06
    푸
    -0.06
    POSITIVE LOGITS
     mat
    0.11
     Mat
    0.09
     mats
    0.08
     Mats
    0.07
    Required
    0.06
    Poster
    0.06
    цією
    0.06
    -stat
    0.06
     Denmark
    0.06
    Ř
    0.06
    Act Density 0.003%

    No Known Activations