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

    Neuronpedia

    INDEX
    Explanations

    years and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appe
    0.65
     traversal
    0.56
     disjoint
    0.55
     sub
    0.53
     shaded
    0.52
     distinct
    0.52
     UTF
    0.51
     lacking
    0.51
     subset
    0.51
     subjug
    0.51
    POSITIVE LOGITS
    7
    1.03
    9
    1.01
    8
    0.97
    6
    0.92
    5
    0.86
    3
    0.83
    4
    0.82
    0
    0.79
    ৭
    0.78
    ৯
    0.77
    Act Density 0.127%

    No Known Activations