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

    Neuronpedia

    INDEX
    Explanations

    Summarizing conclusions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    antha
    -0.06
     boto
    -0.06
    VV
    -0.06
     toReturn
    -0.06
     Operation
    -0.06
     �
    -0.06
     Nếu
    -0.06
    adm
    -0.06
     historia
    -0.06
     omnip
    -0.06
    POSITIVE LOGITS
     BUILD
    0.07
    ije
    0.07
    (tile
    0.07
     Đại
    0.07
    raising
    0.06
    asser
    0.06
     biên
    0.06
    .writeln
    0.06
     lanz
    0.06
     prio
    0.06
    Act Density 0.031%

    No Known Activations