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

    Neuronpedia

    INDEX
    Explanations

    async for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㗊
    0.42
    陏
    0.38
    鞑
    0.37
    Colorful
    0.37
    ذكر
    0.37
    ukiyoe
    0.36
     MODIFY
    0.36
    Disease
    0.36
     වැඩ
    0.36
    ﹝
    0.36
    POSITIVE LOGITS
     class
    0.40
     outputs
    0.39
     kron
    0.37
     ambient
    0.36
     registers
    0.36
     dramas
    0.35
     AVR
    0.35
     output
    0.34
     Kron
    0.34
     ration
    0.33
    Act Density 0.005%

    No Known Activations