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

    Neuronpedia

    INDEX
    Explanations

    lists of information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beo
    0.46
    tir
    0.45
    鲑
    0.45
     пят
    0.44
    нды
    0.44
     it
    0.43
     váy
    0.42
     modifiers
    0.41
     maks
    0.41
     .......
    0.41
    POSITIVE LOGITS
     князя
    0.47
    statistical
    0.45
    讓
    0.45
    mass
    0.44
    Statistical
    0.41
    W
    0.41
    publisher
    0.40
    Anonymous
    0.40
    вами
    0.38
    書店
    0.38
    Act Density 0.001%

    No Known Activations