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

    Neuronpedia

    INDEX
    Explanations

    Mixed media and calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ros
    -0.08
     Clarence
    -0.07
     Rhine
    -0.07
     Rodney
    -0.07
     hollywood
    -0.07
    gever
    -0.07
     Cassidy
    -0.07
     académico
    -0.07
    巴
    -0.07
     روم
    -0.07
    POSITIVE LOGITS
     ಮತ್ತು
    0.12
     आणि
    0.12
     și
    0.12
     àti
    0.12
     ಹಾಗೂ
    0.12
    และ
    0.11
     మరియు
    0.11
     এবং
    0.11
     और
    0.11
     и
    0.11
    Act Density 0.300%

    No Known Activations