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

    Neuronpedia

    INDEX
    Explanations

    raw strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apache
    -0.09
     profitable
    -0.08
     golden
    -0.08
     governance
    -0.08
     경쟁
    -0.07
     previously
    -0.07
    иш
    -0.07
     시장
    -0.07
     atingir
    -0.07
     성공
    -0.07
    POSITIVE LOGITS
     '\\
    0.10
     കോട്ട
    0.09
    (raw
    0.09
    roits
    0.08
     dubbele
    0.08
     Forgot
    0.08
     escapes
    0.08
     দুর্�
    0.08
     Ruta
    0.08
     cliché
    0.08
    Act Density 0.002%

    No Known Activations