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

    Neuronpedia

    INDEX
    Explanations

    cricket wickets, bat, ball

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    懲
    0.39
     συνε
    0.38
     overhead
    0.38
    overhead
    0.37
    界的
    0.37
     Misc
    0.36
     fournisseurs
    0.35
    herd
    0.35
     Overhead
    0.35
    輒
    0.35
    POSITIVE LOGITS
     stumps
    0.84
     crease
    0.57
     creases
    0.57
     timbers
    0.50
     stump
    0.49
     Cre
    0.49
     popping
    0.49
     cre
    0.49
     timber
    0.48
     pops
    0.48
    Act Density 0.002%

    No Known Activations