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

    Neuronpedia

    INDEX
    Explanations

    Coffee and clarified butter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Forward
    -0.08
    ,column
    -0.08
     Column
    -0.08
     Forward
    -0.08
    Violation
    -0.08
     chauffeur
    -0.08
    ,k
    -0.08
    _forward
    -0.08
    .Column
    -0.07
     throwing
    -0.07
    POSITIVE LOGITS
     موسی
    0.09
    เพลง
    0.08
    音
    0.08
     flavors
    0.08
     signals
    0.08
     keywords
    0.08
     ہر
    0.08
    เสียง
    0.08
     aroma
    0.08
     لوب
    0.08
    Act Density 0.007%

    No Known Activations