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

    Neuronpedia

    INDEX
    Explanations

    math examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     =
    0.40
     siempre
    0.40
     pane
    0.39
     inverso
    0.39
     error
    0.38
     sempre
    0.38
     canciones
    0.38
     ky
    0.37
     luogo
    0.37
     ones
    0.37
    POSITIVE LOGITS
     ৭
    0.50
     ৭৫
    0.49
     ৬
    0.48
     १२
    0.47
     $(-
    0.44
     ১৬
    0.43
     ৮
    0.42
     ७
    0.42
     ۱۵
    0.42
     ۷
    0.42
    Act Density 0.006%

    No Known Activations