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

    Neuronpedia

    INDEX
    Explanations

    parentheses/quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     said
    -0.08
     nett
    -0.07
     idiots
    -0.07
     Expedition
    -0.06
     SUCH
    -0.06
    횐
    -0.06
    的东西
    -0.06
    ไอ
    -0.06
     yeti
    -0.06
    .Package
    -0.06
    POSITIVE LOGITS
    olución
    0.08
     Sob
    0.07
    ющих
    0.07
    .XPath
    0.07
    厮
    0.07
    ющее
    0.07
     enclosure
    0.07
    אלוה
    0.07
    并对
    0.07
     turbulent
    0.07
    Act Density 0.014%

    No Known Activations