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

    Neuronpedia

    INDEX
    Explanations

    bomb squad

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Macros
    0.20
     overlays
    0.19
     d
    0.18
     د
    0.18
    이어
    0.17
     ד
    0.17
     darts
    0.16
     ومل
    0.16
     macros
    0.16
    OUIS
    0.16
    POSITIVE LOGITS
     Ka
    0.18
     KA
    0.18
     महज
    0.18
     KPMG
    0.17
     capitalise
    0.17
     Bukan
    0.17
     König
    0.17
    ético
    0.17
     mere
    0.17
     Kawasaki
    0.17
    Act Density 0.009%

    No Known Activations