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

    Neuronpedia

    INDEX
    Explanations

    comparison and contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decision
    0.44
    iter
    0.44
     prosed
    0.42
     keinginan
    0.42
     بتوان
    0.41
     decisão
    0.40
     determinados
    0.40
     frecuente
    0.40
    alaa
    0.40
     beslut
    0.39
    POSITIVE LOGITS
    マスク
    0.48
    績
    0.48
     GPU
    0.46
    ளிக்க
    0.45
    यिक
    0.44
    ється
    0.44
    ه
    0.44
     Blast
    0.43
     GPUs
    0.43
    GPUs
    0.43
    Act Density 0.009%

    No Known Activations