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

    Neuronpedia

    INDEX
    Explanations

    communication and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    1.64
    -/
    1.37
     รวมถึง
    1.14
     (\"
    1.13
     mainly
    1.13
    /"
    1.12
     chiefly
    1.12
     (=
    1.11
     /
    1.09
     mostly
    1.08
    POSITIVE LOGITS
     ஒரு
    0.78
    Một
    0.73
     सम्मान
    0.73
    validator
    0.71
    ஒரு
    0.71
     uncertainty
    0.69
    uncertain
    0.69
    Мы
    0.68
     પ્ર
    0.68
    explore
    0.68
    Act Density 0.202%

    No Known Activations