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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     move
    -0.07
     Networking
    -0.07
    cost
    -0.07
    iman
    -0.07
    Viol
    -0.07
     poisoning
    -0.07
     agent
    -0.07
     MOST
    -0.07
     Edison
    -0.07
     replication
    -0.07
    POSITIVE LOGITS
    ทรง
    0.07
     TextArea
    0.07
    .gamma
    0.07
    른
    0.06
     알아
    0.06
    …
    0.06
    exampleModalLabel
    0.06
    Watching
    0.06
     그러나
    0.06
     mostrar
    0.06
    Act Density 0.019%

    No Known Activations