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

    Neuronpedia

    INDEX
    Explanations

    beams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CDs
    -0.09
    assigned
    -0.08
     cryptocurrencies
    -0.08
     നിയ
    -0.08
     assigned
    -0.08
     来
    -0.07
     workloads
    -0.07
     incubation
    -0.07
    技能
    -0.07
    -ranking
    -0.07
    POSITIVE LOGITS
     plomb
    0.08
     unnoticed
    0.08
     quir
    0.08
     mansion
    0.08
     hus
    0.08
     वास्त
    0.08
    	Check
    0.07
     grime
    0.07
    .Bus
    0.07
     ran
    0.07
    Act Density 0.026%

    No Known Activations