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

    Neuronpedia

    INDEX
    Explanations

    Colossians schemes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.66
    ad
    0.64
    iin
    0.62
    ece
    0.62
    C
    0.62
     चांगली
    0.61
    i
    0.60
     ਮ
    0.59
    ological
    0.58
    ig
    0.57
    POSITIVE LOGITS
     אך
    0.57
    ಂಗ್
    0.55
    Banco
    0.55
     dreamy
    0.55
     comprob
    0.55
    смотрите
    0.54
     colourful
    0.52
     =
    0.52
     Banco
    0.52
     rejoicing
    0.52
    Act Density 0.006%

    No Known Activations