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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rv
    -0.06
    /th
    -0.06
    conte
    -0.06
     THE
    -0.06
     went
    -0.06
     ru
    -0.06
    180
    -0.06
    走
    -0.06
    .RIGHT
    -0.06
     sui
    -0.06
    POSITIVE LOGITS
     accuracy
    0.08
            ↵↵
    0.07
    iд
    0.07
     molec
    0.07
     Απο
    0.07
    uplicated
    0.06
     sequelize
    0.06
    eteor
    0.06
     nabíd
    0.06
     trước
    0.06
    Act Density 0.100%

    No Known Activations