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

    Neuronpedia

    INDEX
    Explanations

    East Asian languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Protocol
    -0.07
     skipping
    -0.06
     word
    -0.06
     certificates
    -0.06
     adopt
    -0.06
     bl
    -0.06
     received
    -0.06
     subjects
    -0.06
     intestine
    -0.06
     switches
    -0.06
    POSITIVE LOGITS
    không
    0.06
    BTN
    0.06
    ič
    0.06
     друг
    0.06
    som
    0.06
     Ale
    0.06
     kor
    0.06
     ​​​
    0.06
    .like
    0.06
    .ColumnName
    0.06
    Act Density 0.024%

    No Known Activations