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

    Neuronpedia

    INDEX
    Explanations

    develop written content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Read
    0.43
     readings
    0.41
    しさ
    0.41
     goat
    0.40
     read
    0.39
     Incorporated
    0.39
     чтения
    0.39
     والمر
    0.39
    READ
    0.38
    inc
    0.38
    POSITIVE LOGITS
    Develop
    0.44
     udvik
    0.44
     разрабо
    0.43
    Development
    0.42
     Entwicklung
    0.41
     Compose
    0.40
    黟
    0.40
    ⓷
    0.40
     развития
    0.39
    Create
    0.38
    Act Density 0.000%

    No Known Activations