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

    Neuronpedia

    INDEX
    Explanations

    sides and perspectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ίζουν
    0.67
     innych
    0.64
     미
    0.61
     대체
    0.59
    alnız
    0.59
     latach
    0.59
     różnych
    0.58
     innymi
    0.57
     উপকারী
    0.55
     वृद्धि
    0.55
    POSITIVE LOGITS
     side
    4.58
     Side
    3.97
    Side
    3.86
    side
    3.63
     SIDE
    3.44
     sides
    3.42
    側
    3.29
    側の
    3.15
     lado
    3.03
    側に
    3.00
    Act Density 0.292%

    No Known Activations