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

    Neuronpedia

    INDEX
    Explanations

    by this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     undergone
    0.43
    ൊന്നും
    0.41
     dugo
    0.39
     arent
    0.38
     niektor
    0.37
     někter
    0.37
    限于
    0.36
    ൂര്‍
    0.36
     bárm
    0.36
     doença
    0.35
    POSITIVE LOGITS
     Dadurch
    1.07
     zodat
    1.04
    これにより
    1.01
    इससे
    0.98
    することで
    0.97
     ताकि
    0.96
     ಇದರಿಂದ
    0.92
     تاکہ
    0.91
     thereby
    0.88
     જેથી
    0.88
    Act Density 0.332%

    No Known Activations