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

    Neuronpedia

    INDEX
    Explanations

    GNU

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contin
    -0.09
     졸
    -0.07
     malls
    -0.07
     adept
    -0.06
     Profile
    -0.06
     своб
    -0.06
     equity
    -0.06
    芬
    -0.06
    payments
    -0.06
     začí
    -0.06
    POSITIVE LOGITS
    .SizeMode
    0.07
    료
    0.06
    ras
    0.06
     información
    0.06
    奥
    0.06
     μην
    0.06
    enth
    0.06
    شناس
    0.06
    /response
    0.06
    \View
    0.06
    Act Density 0.002%

    No Known Activations