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

    Neuronpedia

    INDEX
    Explanations

    assistant analysis of queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     miền
    -0.08
     kami
    -0.08
     feminin
    -0.08
     Clone
    -0.08
     anyị
    -0.08
     Entire
    -0.08
    horn
    -0.08
     Denise
    -0.08
    随后
    -0.08
     전체
    -0.08
    POSITIVE LOGITS
    ，比如
    0.10
     nějak
    0.08
    пр
    0.08
     succ
    0.08
    。不过
    0.07
     క
    0.07
    比如
    0.07
     people's
    0.07
     maybe
    0.07
     czego
    0.07
    Act Density 0.724%

    No Known Activations