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

    Neuronpedia

    INDEX
    Explanations

    reading comprehension monitoring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ונה
    -0.09
     nurturing
    -0.08
    Listed
    -0.08
     કરતાં
    -0.07
     היום
    -0.07
     Boxer
    -0.07
    Letter
    -0.07
    보
    -0.07
    ไทย
    -0.07
     צבע
    -0.07
    POSITIVE LOGITS
     estimation
    0.09
     estimates
    0.09
     अनुमान
    0.08
     Est
    0.08
     Leistungs
    0.08
    IME
    0.08
    zuk
    0.08
     Kontroll
    0.08
    estimate
    0.08
     estimated
    0.08
    Act Density 0.005%

    No Known Activations