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

    Neuronpedia

    INDEX
    Explanations

    numbered list item terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ohn
    0.79
    }',
    0.79
    }')
    0.75
     یورپی
    0.66
    '),
    0.65
    oe
    0.65
    ोग
    0.64
    erd
    0.64
    '}),
    0.64
     мор
    0.64
    POSITIVE LOGITS
     нещо
    0.82
    MessageNow
    0.81
    ispiels
    0.80
     উপায়
    0.80
     அதிசயம்
    0.80
     વસ્તુ
    0.79
     आपसे
    0.79
     اخر
    0.79
     remarque
    0.79
     kidding
    0.79
    Act Density 0.110%

    No Known Activations