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

    Neuronpedia

    INDEX
    Explanations

    pattern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     норматив
    -0.07
     Salle
    -0.07
     соли
    -0.07
     Prescription
    -0.07
    Crew
    -0.07
    (rotation
    -0.07
     salle
    -0.07
     निय
    -0.07
     conductivity
    -0.07
     Noon
    -0.07
    POSITIVE LOGITS
    Wildcard
    0.10
     matcher
    0.10
     wildcard
    0.10
    Matcher
    0.10
     ম্যাচ
    0.10
     പിട
    0.09
    匹
    0.09
    จับ
    0.09
     మ్యాచ్
    0.09
    matching
    0.09
    Act Density 0.003%

    No Known Activations