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

    Neuronpedia

    INDEX
    Explanations

    is enough

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oczywiście
    0.96
    氬
    0.82
     zweite
    0.81
     allgeme
    0.80
    については
    0.79
     externe
    0.79
     uygun
    0.78
     vous
    0.78
     correcto
    0.77
     siku
    0.76
    POSITIVE LOGITS
     enough
    0.69
     beschik
    0.60
    akes
    0.59
    enough
    0.59
     all
    0.59
    ॉक
    0.59
     Wonders
    0.58
     wonders
    0.57
     تسه
    0.56
     revel
    0.55
    Act Density 0.068%

    No Known Activations