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

    Neuronpedia

    INDEX
    Explanations

    type/kind question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ताकि
    -0.08
     दक्ष
    -0.07
     هزینه
    -0.07
     eficiencia
    -0.07
     efficiency
    -0.07
     เพื่อ
    -0.07
    .length
    -0.07
     역사
    -0.07
     understand
    -0.07
     כיצד
    -0.07
    POSITIVE LOGITS
     tende
    0.08
     দিয়
    0.08
    (((
    0.08
     étr
    0.08
     হয়েছিল
    0.08
    ๋
    0.08
    টির
    0.08
    ১৪
    0.08
    ikið
    0.08
    纽
    0.08
    Act Density 0.016%

    No Known Activations