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

    Neuronpedia

    INDEX
    Explanations

    UMMY

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ".↵
    -0.07
     Trash
    -0.06
     ymin
    -0.06
    Trash
    -0.06
    ".
    -0.06
     retreat
    -0.06
    ？」
    -0.06
     Sticky
    -0.06
    .writ
    -0.06
    "[
    -0.06
    POSITIVE LOGITS
    ंजन
    0.07
     subsequently
    0.06
    667
    0.06
    しました
    0.06
    拍
    0.06
    akeup
    0.06
     кон
    0.06
     tack
    0.06
    الد
    0.06
    posit
    0.06
    Act Density 0.000%

    No Known Activations