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

    Neuronpedia

    INDEX
    Explanations

    code error messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elevation
    -0.06
     stopwatch
    -0.06
     intent
    -0.06
     wrestlers
    -0.06
    піон
    -0.06
    企業
    -0.06
     Encounter
    -0.06
    人気
    -0.06
     Insights
    -0.06
     client
    -0.05
    POSITIVE LOGITS
     dolaş
    0.07
    /article
    0.07
    ,’”
    0.07
    racak
    0.06
    ाधन
    0.06
    COM
    0.06
    كوم
    0.06
    <u
    0.06
     รวม
    0.06
     exped
    0.06
    Act Density 0.051%

    No Known Activations