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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interface
    -0.07
     handsome
    -0.07
     interfaces
    -0.06
    zug
    -0.06
     technically
    -0.06
     eligibility
    -0.06
     broker
    -0.06
     rookie
    -0.06
    _cat
    -0.06
     agent
    -0.06
    POSITIVE LOGITS
    posix
    0.06
    razil
    0.06
    ",&
    0.06
     Pet
    0.06
     Seas
    0.06
     Серед
    0.06
    .lastIndexOf
    0.06
    انات
    0.06
    Different
    0.06
     sayısı
    0.06
    Act Density 0.035%

    No Known Activations