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

    Neuronpedia

    INDEX
    Explanations

    units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    finder
    -0.08
     ç
    -0.07
     kính
    -0.07
    (pr
    -0.07
     print
    -0.07
    كومة
    -0.07
     Bf
    -0.07
     T
    -0.06
     सब
    -0.06
    	gl
    -0.06
    POSITIVE LOGITS
    elas
    0.07
    lem
    0.07
     Valle
    0.07
    les
    0.06
     Louisiana
    0.06
     Candle
    0.06
    _UDP
    0.06
     Who
    0.06
     ราย
    0.06
    kel
    0.06
    Act Density 0.000%

    No Known Activations