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

    Neuronpedia

    INDEX
    Explanations

    adoption used later

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Juice
    0.43
     ಆಹಾರ
    0.40
     முருக
    0.39
     exemplifies
    0.39
     ferroc
    0.39
     Bistro
    0.38
     enzymatic
    0.38
     Fiberglass
    0.38
          
    0.38
    quoting
    0.38
    POSITIVE LOGITS
     мра
    0.41
    ían
    0.40
     अत्याचार
    0.40
     crumble
    0.39
    жают
    0.38
     адво
    0.38
    itab
    0.37
     само
    0.37
     ее
    0.37
     scams
    0.37
    Act Density 0.002%

    No Known Activations