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

    Neuronpedia

    INDEX
    Explanations

    italian cities and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dilwale
    0.53
     contentious
    0.49
     inherently
    0.47
     proactive
    0.47
     cheerio
    0.46
     snowflake
    0.46
     andrew
    0.46
     cohesive
    0.45
     plunger
    0.45
     داله
    0.45
    POSITIVE LOGITS
     Castel
    0.89
    Monte
    0.88
     San
    0.86
     Monte
    0.86
     Bologna
    0.85
     Castello
    0.84
     Sant
    0.82
    San
    0.81
     Santa
    0.80
     Cast
    0.79
    Act Density 0.008%

    No Known Activations