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

    Neuronpedia

    INDEX
    Explanations

    Beginner to Beyond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     случаев
    0.75
    гії
    0.74
    aitement
    0.66
     পররাষ্ট্র
    0.65
    ibu
    0.64
     આવે
    0.63
    េរ
    0.63
     écoul
    0.63
     ferries
    0.63
     মাহবুব
    0.62
    POSITIVE LOGITS
     mash
    0.73
     Moran
    0.71
     ksi
    0.71
     dumb
    0.68
     harden
    0.68
     expl
    0.66
     harder
    0.66
     culmin
    0.64
     runt
    0.64
     puc
    0.63
    Act Density 0.000%

    No Known Activations