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

    Neuronpedia

    INDEX
    Explanations

    remaining options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    বিভিন্ন
    0.93
     berbagai
    0.92
     Various
    0.89
     বিভিন্ন
    0.86
    various
    0.85
     różne
    0.85
    Various
    0.84
    Within
    0.84
     Within
    0.84
     각종
    0.81
    POSITIVE LOGITS
     others
    1.16
     counterparts
    1.06
     counterpart
    0.97
     الثانية
    0.94
    others
    0.94
     subsequent
    0.92
     나머지
    0.91
     الثانيه
    0.90
    Others
    0.89
    另一
    0.89
    Act Density 0.306%

    No Known Activations