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

    Neuronpedia

    INDEX
    Explanations

    performing tasks or duties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ատ
    0.46
    任務
    0.44
    Roboto
    0.42
    ',{
    0.40
    ീതി
    0.40
     snelheid
    0.39
     przewod
    0.39
     TASK
    0.38
    Renderer
    0.38
    疼痛
    0.38
    POSITIVE LOGITS
     arithmetic
    0.45
     work
    0.43
     embellished
    0.42
     job
    0.42
     down
    0.40
     upbeat
    0.40
     scholarships
    0.40
     cupcakes
    0.39
     flourishes
    0.39
     main
    0.39
    Act Density 0.000%

    No Known Activations