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

    Neuronpedia

    INDEX
    Explanations

    HTML snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FROM
    -0.07
    .sigma
    -0.06
    WEST
    -0.06
     PX
    -0.06
    reports
    -0.06
    564
    -0.06
     भ
    -0.06
    822
    -0.06
    PEND
    -0.06
    warf
    -0.06
    POSITIVE LOGITS
    rans
    0.06
    ,“
    0.06
    Additional
    0.06
     bruk
    0.06
     konci
    0.06
     期
    0.06
    <pair
    0.06
     phổ
    0.06
    کرد
    0.06
    .index
    0.06
    Act Density 0.031%

    No Known Activations