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

    Neuronpedia

    INDEX
    Explanations

    list numbers and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಚಿತ
    0.53
    定的
    0.46
    িসি
    0.46
    níka
    0.44
    :...
    0.44
    Результа
    0.43
    ніза
    0.42
    ড়ে
    0.42
    높
    0.40
     পরিবর্তনের
    0.40
    POSITIVE LOGITS
     estan
    0.46
    などの
    0.45
     classica
    0.44
     ،
    0.44
     इनमें
    0.43
     etc
    0.42
     classiques
    0.42
     उनमें
    0.42
     populares
    0.42
     ಹಾಗೂ
    0.42
    Act Density 0.000%

    No Known Activations