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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sanitation
    -0.07
     lodash
    -0.07
     Sınıf
    -0.07
    âu
    -0.07
    環
    -0.07
    ollah
    -0.07
     charitable
    -0.06
    ampp
    -0.06
     ming
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    Nov
    0.06
     ayn
    0.06
    chner
    0.06
    leading
    0.06
    (insert
    0.06
     росій
    0.06
     irre
    0.06
     снова
    0.06
    .Box
    0.06
     Guam
    0.06
    Act Density 0.057%

    No Known Activations