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

    Neuronpedia

    INDEX
    Explanations

    programming tools and collaboration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sensor
    0.44
     krwi
    0.44
     sensores
    0.44
     미래
    0.43
     Sensors
    0.42
     tervez
    0.42
     assimil
    0.42
     komplik
    0.42
    मेय
    0.42
     Jersey
    0.41
    POSITIVE LOGITS
    a
    0.49
    γν
    0.42
     بأ
    0.40
    चा
    0.39
    Family
    0.39
    country
    0.39
    AddItem
    0.39
    own
    0.39
    Monter
    0.39
    ง
    0.39
    Act Density 0.003%

    No Known Activations