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

    Neuronpedia

    INDEX
    Explanations

    For

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     теперь
    -0.07
    _photo
    -0.07
    said
    -0.07
     Sugar
    -0.07
     Task
    -0.07
    σμός
    -0.06
     الأمر
    -0.06
     naam
    -0.06
     Race
    -0.06
     ett
    -0.06
    POSITIVE LOGITS
     mẽ
    0.07
    ologne
    0.07
     ipad
    0.07
    )").
    0.07
    BV
    0.06
     εμπ
    0.06
    [jj
    0.06
    DownList
    0.06
    :true
    0.06
    ".↵
    0.06
    Act Density 0.002%

    No Known Activations