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

    Neuronpedia

    INDEX
    Explanations

    lack substantial capacity to appreciate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    গিত
    0.38
    OnFileChange
    0.38
    भेद
    0.36
     vergessen
    0.36
     ಭಾವ
    0.35
    摸
    0.35
    のため
    0.35
    lanelet
    0.35
    辍
    0.35
     Horne
    0.35
    POSITIVE LOGITS
     engineered
    0.38
     locaux
    0.38
    engineered
    0.38
     Engineered
    0.37
     Outcomes
    0.37
     Rift
    0.37
     results
    0.36
     Rij
    0.36
     Locally
    0.36
     Barclays
    0.35
    Act Density 0.000%

    No Known Activations