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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jei
    -0.08
    �
    -0.08
    .Js
    -0.08
     verða
    -0.08
     संग्रह
    -0.08
     दिन
    -0.07
     inm
    -0.07
     prender
    -0.07
    ytorch
    -0.07
     jorn
    -0.07
    POSITIVE LOGITS
     erhöht
    0.08
     environs
    0.08
     என்பது
    0.08
    więks
    0.08
     бу
    0.08
     கட
    0.07
    рав
    0.07
    值
    0.07
    by
    0.07
     Bu
    0.07
    Act Density 0.052%

    No Known Activations