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

    Neuronpedia

    INDEX
    Explanations

    reporting words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     neby
    -0.06
    脚
    -0.06
     Democratic
    -0.06
     sánh
    -0.06
    _detected
    -0.06
    Db
    -0.06
    .fin
    -0.06
     spoiled
    -0.06
     гід
    -0.06
    .FC
    -0.06
    POSITIVE LOGITS
     Croatia
    0.07
     anzeigen
    0.07
    APPED
    0.07
    ilians
    0.07
    _rename
    0.07
     Zucker
    0.07
    flen
    0.06
     getUserId
    0.06
    mAh
    0.06
    .Native
    0.06
    Act Density 0.011%

    No Known Activations