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

    Neuronpedia

    INDEX
    Explanations

    say "selection"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ví
    -0.07
    Food
    -0.07
    align
    -0.06
    讨
    -0.06
    RAW
    -0.06
    link
    -0.06
    Mode
    -0.06
     iCloud
    -0.06
     Food
    -0.06
     estad
    -0.06
    POSITIVE LOGITS
    Fortunately
    0.06
     formations
    0.06
    AZ
    0.06
     Scholars
    0.06
    '>{
    0.06
     فصل
    0.06
    .rollback
    0.06
     treffen
    0.06
    Interestingly
    0.06
    .setCurrent
    0.06
    Act Density 0.076%

    No Known Activations