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

    Neuronpedia

    INDEX
    Explanations

    network communication handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     evap
    0.42
    RAP
    0.41
     acum
    0.41
     floc
    0.41
    gum
    0.40
    GraphQL
    0.40
    rapid
    0.40
     esqu
    0.40
     Vimeo
    0.39
     तनु
    0.39
    POSITIVE LOGITS
     comunicación
    0.82
     threaded
    0.80
     communication
    0.79
     Socket
    0.79
     socket
    0.79
     threads
    0.76
     thread
    0.76
     threading
    0.76
     Thread
    0.75
    通信
    0.74
    Act Density 0.011%

    No Known Activations