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

    Neuronpedia

    INDEX
    Explanations

    numerical increase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (center
    -0.06
    Venta
    -0.06
     prescriptions
    -0.06
    (cls
    -0.06
     SharedPreferences
    -0.06
    RG
    -0.06
    ARIABLE
    -0.06
     Roc
    -0.06
    berra
    -0.06
    (inputs
    -0.06
    POSITIVE LOGITS
     swelling
    0.07
    ुष
    0.07
     Noble
    0.07
     Dut
    0.07
     legally
    0.06
     gorgeous
    0.06
     corrective
    0.06
    識
    0.06
    Σ
    0.06
     Planner
    0.06
    Act Density 0.043%

    No Known Activations