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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Akan
    -0.08
     Shorts
    -0.08
     Imagine
    -0.08
     Deletes
    -0.08
     Ess
    -0.08
     cread
    -0.07
     shorts
    -0.07
    amp
    -0.07
    kab
    -0.07
     രണ്ട്
    -0.07
    POSITIVE LOGITS
    هاز
    0.08
     등의
    0.07
    Although
    0.07
    Despite
    0.07
    506
    0.07
     판매
    0.07
     도시
    0.07
    �
    0.07
    Alternate
    0.07
    ैत
    0.07
    Act Density 0.000%

    No Known Activations