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

    Neuronpedia

    INDEX
    Explanations

    where

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Beat
    -0.07
     THROUGH
    -0.07
     "()
    -0.06
    .ZERO
    -0.06
     Dortmund
    -0.06
     Roe
    -0.06
     �
    -0.06
     난
    -0.06
    322
    -0.06
    등록
    -0.06
    POSITIVE LOGITS
     impr
    0.07
    ा।↵
    0.07
     Мар
    0.07
     \
    0.06
    sizlik
    0.06
     где
    0.06
     часом
    0.06
     där
    0.06
     where
    0.06
    μεν
    0.06
    Act Density 0.032%

    No Known Activations