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

    Neuronpedia

    INDEX
    Explanations

    file operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    package
    0.45
     Established
    0.43
     Go
    0.41
    卫星
    0.41
     satellite
    0.41
     Satellite
    0.39
     ktor
    0.39
     Receiving
    0.39
     טי
    0.38
     Startup
    0.38
    POSITIVE LOGITS
     있지
    0.40
    Dos
    0.39
     dos
    0.38
     displace
    0.38
    なんて
    0.38
     поза
    0.38
    Lone
    0.38
    DOS
    0.38
     забу
    0.37
     stuffed
    0.37
    Act Density 0.008%

    No Known Activations