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

    Neuronpedia

    INDEX
    Explanations

    butter or taste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noodles
    0.44
    živ
    0.42
     Candles
    0.41
     Noodles
    0.41
     chromos
    0.39
    ذف
    0.38
     haircuts
    0.38
    iph
    0.38
     iPhones
    0.38
    ລາ
    0.38
    POSITIVE LOGITS
     जोकि
    0.38
    어도
    0.37
    প্যাথ
    0.37
    мага
    0.36
    ermek
    0.36
    Setup
    0.36
     AdapterView
    0.36
     slutt
    0.36
    кут
    0.36
    чен
    0.35
    Act Density 0.000%

    No Known Activations