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

    Neuronpedia

    INDEX
    Explanations

    end of sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াক
    1.04
     cohom
    1.01
     outskirts
    0.96
     secretions
    0.92
     arterioles
    0.89
     arterial
    0.86
     denitrification
    0.84
    ма
    0.84
     permeates
    0.83
     ellipso
    0.82
    POSITIVE LOGITS
    тся
    1.02
    ี
    0.90
     użytk
    0.89
    the
    0.86
    d
    0.81
    있
    0.80
    omány
    0.80
    없는
    0.80
    면
    0.80
    吧
    0.80
    Act Density 0.003%

    No Known Activations