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

    Neuronpedia

    INDEX
    Explanations

    cte

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     workable
    -0.08
     portraying
    -0.08
     outright
    -0.08
     beginnings
    -0.07
    Analy
    -0.07
     год
    -0.07
     declar
    -0.07
    ako
    -0.07
    Portfolio
    -0.07
    arl
    -0.07
    POSITIVE LOGITS
    期间
    0.15
     દરમિયાન
    0.14
     दौरान
    0.14
     દરમ
    0.13
    过程中
    0.12
     aikana
    0.12
    遇
    0.11
     sırasında
    0.11
     동안
    0.11
    ثناء
    0.11
    Act Density 0.094%

    No Known Activations