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

    Neuronpedia

    INDEX
    Explanations

    after common prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.50
    ’
    0.46
     r
    0.45
     o
    0.45
    aroni
    0.45
     can
    0.43
    atta
    0.42
     is
    0.41
     value
    0.41
     ;
    0.41
    POSITIVE LOGITS
     நக
    0.59
    ेडियम
    0.58
    CreateParams
    0.57
     நூற்றாண்டின்
    0.54
     ಪ್ರದೇಶ
    0.51
     panneaux
    0.51
    Buildings
    0.50
     напряжения
    0.49
     parque
    0.49
    ျေး
    0.49
    Act Density 0.055%

    No Known Activations