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

    Neuronpedia

    INDEX
    Explanations

    mid-range / intermediate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bottom
    0.54
    Bottom
    0.53
    W
    0.52
     Wald
    0.51
    ஸின்
    0.51
    any
    0.50
     सबै
    0.50
    7
    0.50
    br
    0.49
    even
    0.49
    POSITIVE LOGITS
     intermediate
    1.07
     Intermediate
    1.01
    intermediate
    0.98
    Intermediate
    0.93
     intermédiaire
    0.93
     intermediates
    0.87
     중간
    0.80
     midrange
    0.79
    次は
    0.77
     intermediary
    0.76
    Act Density 0.891%

    No Known Activations