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

    Neuronpedia

    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Сьогодні
    0.54
    スイーツ
    0.52
    IsResolver
    0.51
     ხელისუფლების
    0.51
     ಮಾತ್ರ
    0.50
     veracity
    0.50
     ठाकरे
    0.50
     сьогодні
    0.50
    ollary
    0.48
    cevam
    0.48
    POSITIVE LOGITS
     and
    0.67
    ,
    0.53
    !
    0.52
    c
    0.48
     d
    0.47
     rabbit
    0.46
     &
    0.45
    0
    0.45
    and
    0.45
     a
    0.44
    Act Density 0.003%

    No Known Activations